Skip to main content

Sanja Fidler

University of Toronto, Computer Science, Faculty Member

Followers

12

Following

3

Co-authors

3

Public Views

School of the Art Institute of Chicago

Julita Vassileva

University of Saskatchewan

Knox College

Duke University

Oxford Brookes University

Roshan Chitrakar

Nepal College of Information Technology

Graduate Center of the City University of New York

PALIMOTE JUSTICE

RIVERS STATE POLYTECHNIC

Punjab Technical University

Christopher Crick

Oklahoma State University

Interests

Uploads

Papers by Sanja Fidler

Human-Machine CRFs for Identifying Bottlenecks in Scene Understanding

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015

Recent trends in image understanding have pushed for scene understanding models that jointly reas... more Recent trends in image understanding have pushed for scene understanding models that jointly reason about various tasks such as object detection, scene recognition, shape analysis, contextual reasoning, and local appearance based classifiers. In this work, we are interested in understanding the roles of these different tasks in improved scene understanding, in particular semantic segmentation, object detection and scene recognition. Towards this goal, we &quot;plug-in&quot; human subjects for each of the various components in a conditional random field model. Comparisons among various hybrid human-machine CRFs give us indications of how much &quot;head room&quot; there is to improve scene understanding by focusing research efforts on various individual tasks.

Selecting features for object detection using an AdaBoost-compatible evaluation function

by Sanja Fidler, Aleš Leonardis, and Luka Fürst

Pattern Recognition Letters, 2008

This paper addresses the problem of selecting features in a visual object detection setup where a... more This paper addresses the problem of selecting features in a visual object detection setup where a detection algorithm is applied to an input image represented by a set of features. The set of features to be employed in the test stage is prepared in two training-stage steps. In the first step, a feature extraction algorithm produces a (possibly large) initial set of features. In the second step, on which this paper focuses, the initial set is reduced using a selection procedure. The proposed selection procedure is based on a novel evaluation function that measures the utility of individual features for a certain detection task. Owing to its design, the evaluation function can be seamlessly embedded into an AdaBoost selection framework. The developed selection procedure is integrated with state-of-the-art feature extraction and object detection methods. The presented system was tested on five challenging detection setups. In three of them, a fairly high detection accuracy was effected by as few as six features selected out of several hundred initial candidates.

Towards Scalable Representations of Object Categories: Learning a Hierarchy of Parts

by Sanja Fidler and Aleš Leonardis

2007 IEEE Conference on Computer Vision and Pattern Recognition, 2007

This paper proposes a novel approach to constructing a hierarchical representation of visual inpu... more This paper proposes a novel approach to constructing a hierarchical representation of visual input that aims to enable recognition and detection of a large number of object categories. Inspired by the principles of efficient indexing (bottom-up), robust matching (top-down), and ideas of compositionality, our approach learns a hierarchy of spatially flexible compositions, i.e. parts, in an unsupervised, statistics-driven manner. Starting with simple, frequent features, we learn the statistically most significant compositions (parts composed of parts), which consequently define the next layer. Parts are learned sequentially, layer after layer, optimally adjusting to the visual data. Lower layers are learned in a category-independent way to obtain complex, yet sharable visual building blocks, which is a crucial step towards a scalable representation. Higher layers of the hierarchy, on the other hand, are constructed by using specific categories, achieving a category representation with a small number of highly generalizable parts that gained their structural flexibility through composition within the hierarchy. Built in this way, new categories can be efficiently and continuously added to the system by adding a small number of parts only in the higher layers. The approach is demonstrated on a large collection of images and a variety of object categories. Detection results confirm the effectiveness and robustness of the learned parts. * This research has been supported in part by: Research program P2-0214 (RS), EU FP6-004250-IP project CoSy, and EU FP6-511051-2 project MOBVIS.

Learning Hierarchical Representations of Object Categories for Robot Vision

by Sanja Fidler and Aleš Leonardis

Springer Tracts in Advanced Robotics, 2010

This paper presents our recently developed approach to constructing a hierarchical representation... more This paper presents our recently developed approach to constructing a hierarchical representation of visual input that aims to enable recognition and detection of a large number of object categories. Inspired by the principles of efficient indexing, robust matching, and ideas of compositionality, our approach learns a hierarchy of spatially flexible compositions, i.e. parts, in an unsupervised, statistics-driven manner. Starting with simple, frequent features, we learn the statistically most significant compositions (parts composed of parts), which consequently define the next layer. Parts are learned sequentially, layer after layer, optimally adjusting to the visual data. Lower layers are learned in a category-independent way to obtain complex, yet sharable visual building blocks, which is a crucial step towards a scalable representation. Higher layers of the hierarchy, on the other hand, are constructed by using specific categories, achieving a category representation with a small number of highly generalizable parts that gained their structural flexibility through composition within the hierarchy. Built in this way, new categories can be efficiently and continuously added to the system by adding a small number of parts only in the higher layers. The approach is demonstrated on a large collection of images and a variety of object categories.

The Role of Context for Object Detection and Semantic Segmentation in the Wild

2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014

In this paper we study the role of context in existing stateof-the-art detection and segmentation... more In this paper we study the role of context in existing stateof-the-art detection and segmentation approaches. Towards this goal, we label every pixel of PASCAL VOC 2010 detection challenge with a semantic category. We believe this data will provide plenty of challenges to the community, as it contains 520 additional classes for semantic segmentation and object detection. Our analysis shows that nearest neighbor based approaches perform poorly on semantic segmentation of contextual classes, showing the variability of PASCAL imagery. Furthermore, improvements of existing contextual models for detection is rather modest. In order to push forward the performance in this difficult scenario, we propose a novel deformable part-based model, which exploits both local context around each candidate detection as well as global context at the level of the scene. We show that this contextual reasoning significantly helps in detecting objects at all scales.

Detect What You Can: Detecting and Representing Objects Using Holistic Models and Body Parts

2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014

Detecting objects becomes difficult when we need to deal with large shape deformation, occlusion ... more Detecting objects becomes difficult when we need to deal with large shape deformation, occlusion and low resolution. We propose a novel approach to i) handle large deformations and partial occlusions in animals (as examples of highly deformable objects), ii) describe them in terms of body parts, and iii) detect them when their body parts are hard to detect (e.g., animals depicted at low resolution). We represent the holistic object and body parts separately and use a fully connected model to arrange templates for the holistic object and body parts. Our model automatically decouples the holistic object or body parts from the model when they are hard to detect. This enables us to represent a large number of holistic object and body part combinations to better deal with different "detectability" patterns caused by deformations, occlusion and/or low resolution.

What Are You Talking About? Text-to-Image Coreference

2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014

In this paper we exploit natural sentential descriptions of RGB-D scenes in order to improve 3D s... more In this paper we exploit natural sentential descriptions of RGB-D scenes in order to improve 3D semantic parsing. Importantly, in doing so, we reason about which particular object each noun/pronoun is referring to in the image. This allows us to utilize visual information in order to disambiguate the so-called coreference resolution problem that arises in text. Towards this goal, we propose a structure prediction model that exploits potentials computed from text and RGB-D imagery to reason about the class of the 3D objects, the scene type, as well as to align the nouns/pronouns with the referred visual objects. We demonstrate the effectiveness of our approach on the challenging NYU-RGBD v2 dataset, which we enrich with natural lingual descriptions. We show that our approach significantly improves 3D detection and scene classification accuracy, and is able to reliably estimate the text-to-image alignment. Furthermore, by using textual and visual information, we are also able to successfully deal with coreference in text, improving upon the state-of-the-art Stanford coreference system .

Box in the Box: Joint 3D Layout and Object Reasoning from Single Images

2013 IEEE International Conference on Computer Vision, 2013

In this paper we propose an approach to jointly infer the room layout as well as the objects pres... more In this paper we propose an approach to jointly infer the room layout as well as the objects present in the scene. Towards this goal, we propose a branch and bound algorithm which is guaranteed to retrieve the global optimum of the joint problem. The main difficulty resides in taking into account occlusion in order to not over-count the evidence. We introduce a new decomposition method, which generalizes integral geometry to triangular shapes, and allows us to bound the different terms in constant time. We exploit both geometric cues and object detectors as image features and show large improvements in 2D and 3D object detection over state-of-the-art deformable part-based models.

Beat the MTurkers: Automatic Image Labeling from Weak 3D Supervision

2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014

Labeling large-scale datasets with very accurate object segmentations is an elaborate task that r... more Labeling large-scale datasets with very accurate object segmentations is an elaborate task that requires a high degree of quality control and a budget of tens or hundreds of thousands of dollars. Thus, developing solutions that can automatically perform the labeling given only weak supervision is key to reduce this cost. In this paper, we show how to exploit 3D information to automatically generate very accurate object segmentations given annotated 3D bounding boxes. We formulate the problem as the one of inference in a binary Markov random field which exploits appearance models, stereo and/or noisy point clouds, a repository of 3D CAD models as well as topological constraints. We demonstrate the effectiveness of our approach in the context of autonomous driving, and show that we can segment cars with the accuracy of 86% intersection-over-union, performing as well as highly recommended MTurkers!

Categorical Perception

by Sanja Fidler and Aleš Leonardis

Cognitive Systems Monographs, 2010

Page 1. 4 Categorical Perception Mario Fritz1, Mykhaylo Andriluka1, Sanja Fidler2, Michael Stark1... more

3D Object Detection with a Deformable 3D Cuboid Model

Supplementary material: A Sentence is Worth a Thousand Pixels

Supplementary Material: Analyzing Semantic Segmentation Using Hybrid Human-Machine CRFs

Describing the Scene as a Whole: Joint Object Detection

In this paper we propose an approach to holistic scene understanding that reasons jointly about r... more In this paper we propose an approach to holistic scene understanding that reasons jointly about regions, location, class and spatial extent of objects, presence of a class in the image, as well as the scene type. Learning and inference in our model are efficient as we reason at the segment level, and introduce auxiliary variables that allow us to decompose the inherent high-order potentials into pairwise potentials between a few variables with small number of states (at most the number of classes). Inference is done via a convergent message-passing algorithm, which, unlike graph-cuts inference, has no submodularity restrictions and does not require potential specific moves. We believe this is very important, as it allows us to encode our ideas and prior knowledge about the problem without the need to change the inference engine every time we introduce a new potential. Our approach outperforms the state-of-the-art on the MSRC-21 benchmark, while being much faster. Importantly, our holistic model is able to improve performance in all tasks.

Learning a hierarchical compositional shape vocabulary for multi-class object representation

Hierarchies allow feature sharing between objects at multiple levels of representation, can code ... more Hierarchies allow feature sharing between objects at multiple levels of representation, can code exponential variability in a very compact way and enable fast inference. This makes them potentially suitable for learning and recognizing a higher number of object classes. However, the success of the hierarchical approaches so far has been hindered by the use of hand-crafted features or predetermined grouping rules. This paper presents a novel framework for learning a hierarchical compositional shape vocabulary for representing multiple object classes. The approach takes simple contour fragments and learns their frequent spatial configurations. These are recursively combined into increasingly more complex and class-specific shape compositions, each exerting a high degree of shape variability. At the top-level of the vocabulary, the compositions are sufficiently large and complex to represent the whole shapes of the objects. We learn the vocabulary layer after layer, by gradually increasing the size of the window of analysis and reducing the spatial resolution at which the shape configurations are learned. The lower layers are learned jointly on images of all classes, whereas the higher layers of the vocabulary are learned incrementally, by presenting the algorithm with one object class after another. The experimental results show that the learned multi-class object representation scales favorably with the number of object classes and achieves a state-of-the-art detection performance at both, faster inference as well as shorter training times.

segDeepM: Exploiting Segmentation and Context in Deep Neural Networks for Object Detection

In this paper, we propose an approach that exploits object segmentation in order to improve the a... more In this paper, we propose an approach that exploits object segmentation in order to improve the accuracy of object detection. We frame the problem as inference in a Markov Random Field, in which each detection hypothesis scores object appearance as well as contextual information using Convolutional Neural Networks, and allows the hypothesis to choose and score a segment out of a large pool of accurate object segmentation proposals. This enables the detector to incorporate additional evidence when it is available and thus results in more accurate detections. Our experiments show an improvement of 4.1% in mAP over the R-CNN baseline on PASCAL VOC 2010, and 3.4% over the current state-of-the-art, demonstrating the power of our approach.

Visual semantic search: Retrieving videos via complex textual queries

In this paper, we tackle the problem of retrieving videos using complex natural language queries.... more In this paper, we tackle the problem of retrieving videos using complex natural language queries. Towards this goal, we first parse the sentential descriptions into a semantic graph, which is then matched to visual concepts using a generalized bipartite matching algorithm. Our approach exploits object appearance, motion and spatial relations, and learns the importance of each term using structure prediction. We demonstrate the effectiveness of our approach on a new dataset designed for semantic search in the context of autonomous driving, which exhibits complex and highly dynamic scenes with many objects. We show that our approach is able to locate a major portion of the objects described in the query with high accuracy, and improve the relevance in video retrieval.

Holistic scene understanding for 3d object detection with rgbd cameras

In this paper, we tackle the problem of indoor scene understanding using RGBD data. Towards this ... more In this paper, we tackle the problem of indoor scene understanding using RGBD data. Towards this goal, we propose a holistic approach that exploits 2D segmentation, 3D geometry, as well as contextual relations between scenes and objects. Specifically, we extend the CPMC [3] framework to 3D in order to generate candidate cuboids, and develop a conditional random field to integrate information from different sources to classify the cuboids. With this formulation, scene classification and 3D object recognition are coupled and can be jointly solved through probabilistic inference. We test the effectiveness of our approach on the challenging NYU v2 dataset. The experimental results demonstrate that through effective evidence integration and holistic reasoning, our approach achieves substantial improvement over the state-of-the-art.

$Figure 4. Comparison of different methods in cuboid detection. Performance measured in recall, i.e. the fraction of objects which are covered by at least one candidate cube (with overlap > 0.5.)$

Bottom-up Segmentation for Top-down Detection

In this paper we are interested in how semantic segmentation can help object detection. Towards t... more In this paper we are interested in how semantic segmentation can help object detection. Towards this goal, we propose a novel deformable part-based model which exploits region-based segmentation algorithms that compute candidate object regions by bottom-up clustering followed by ranking of those regions. Our approach allows every detection hypothesis to select a segment (including void), and scores each box in the image using both the traditional HOG filters as well as a set of novel segmentation features. Thus our model "blends" between the detector and segmentation models. Since our features can be computed very efficiently given the segments, we maintain the same complexity as the original DPM . We demonstrate the effectiveness of our approach in PASCAL VOC 2010, and show that when employing only a root filter our approach outperforms Dalal & Triggs detector [12] on all classes, achieving 13% higher average AP. When employing the parts, we outperform the original DPM in 19 out of 20 classes, achieving an improvement of 8% AP. Furthermore, we outperform the previous state-of-the-art on VOC'10 test by 4%.

Analyzing Semantic Segmentation Using Hybrid Human-Machine CRFs

2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013

Recent trends in semantic image segmentation have pushed for holistic scene understanding models ... more Recent trends in semantic image segmentation have pushed for holistic scene understanding models that jointly reason about various tasks such as object detection, scene recognition, shape analysis, contextual reasoning. In this work, we are interested in understanding the roles of these different tasks in aiding semantic segmentation. Towards this goal, we "plug-in" human subjects for each of the various components in a state-of-the-art conditional random field model (CRF) on the MSRC dataset. Comparisons among various hybrid human-machine CRFs give us indications of how much "head room" there is to improve segmentation by focusing research efforts on each of the tasks. One of the interesting findings from our slew of studies was that human classification of isolated super-pixels, while being worse than current machine classifiers, provides a significant boost in performance when plugged into the CRF! Fascinated by this finding, we conducted in depth analysis of the human generated potentials. This inspired a new machine potential which significantly improves state-of-the-art performance on the MRSC dataset.

Human-Machine CRFs for Identifying Bottlenecks in Scene Understanding

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015

Recent trends in image understanding have pushed for scene understanding models that jointly reas... more Recent trends in image understanding have pushed for scene understanding models that jointly reason about various tasks such as object detection, scene recognition, shape analysis, contextual reasoning, and local appearance based classifiers. In this work, we are interested in understanding the roles of these different tasks in improved scene understanding, in particular semantic segmentation, object detection and scene recognition. Towards this goal, we &quot;plug-in&quot; human subjects for each of the various components in a conditional random field model. Comparisons among various hybrid human-machine CRFs give us indications of how much &quot;head room&quot; there is to improve scene understanding by focusing research efforts on various individual tasks.

Selecting features for object detection using an AdaBoost-compatible evaluation function

by Sanja Fidler, Aleš Leonardis, and Luka Fürst

Pattern Recognition Letters, 2008

This paper addresses the problem of selecting features in a visual object detection setup where a... more This paper addresses the problem of selecting features in a visual object detection setup where a detection algorithm is applied to an input image represented by a set of features. The set of features to be employed in the test stage is prepared in two training-stage steps. In the first step, a feature extraction algorithm produces a (possibly large) initial set of features. In the second step, on which this paper focuses, the initial set is reduced using a selection procedure. The proposed selection procedure is based on a novel evaluation function that measures the utility of individual features for a certain detection task. Owing to its design, the evaluation function can be seamlessly embedded into an AdaBoost selection framework. The developed selection procedure is integrated with state-of-the-art feature extraction and object detection methods. The presented system was tested on five challenging detection setups. In three of them, a fairly high detection accuracy was effected by as few as six features selected out of several hundred initial candidates.

Towards Scalable Representations of Object Categories: Learning a Hierarchy of Parts

by Sanja Fidler and Aleš Leonardis

2007 IEEE Conference on Computer Vision and Pattern Recognition, 2007

This paper proposes a novel approach to constructing a hierarchical representation of visual inpu... more This paper proposes a novel approach to constructing a hierarchical representation of visual input that aims to enable recognition and detection of a large number of object categories. Inspired by the principles of efficient indexing (bottom-up), robust matching (top-down), and ideas of compositionality, our approach learns a hierarchy of spatially flexible compositions, i.e. parts, in an unsupervised, statistics-driven manner. Starting with simple, frequent features, we learn the statistically most significant compositions (parts composed of parts), which consequently define the next layer. Parts are learned sequentially, layer after layer, optimally adjusting to the visual data. Lower layers are learned in a category-independent way to obtain complex, yet sharable visual building blocks, which is a crucial step towards a scalable representation. Higher layers of the hierarchy, on the other hand, are constructed by using specific categories, achieving a category representation with a small number of highly generalizable parts that gained their structural flexibility through composition within the hierarchy. Built in this way, new categories can be efficiently and continuously added to the system by adding a small number of parts only in the higher layers. The approach is demonstrated on a large collection of images and a variety of object categories. Detection results confirm the effectiveness and robustness of the learned parts. * This research has been supported in part by: Research program P2-0214 (RS), EU FP6-004250-IP project CoSy, and EU FP6-511051-2 project MOBVIS.

Learning Hierarchical Representations of Object Categories for Robot Vision

by Sanja Fidler and Aleš Leonardis

Springer Tracts in Advanced Robotics, 2010

This paper presents our recently developed approach to constructing a hierarchical representation... more This paper presents our recently developed approach to constructing a hierarchical representation of visual input that aims to enable recognition and detection of a large number of object categories. Inspired by the principles of efficient indexing, robust matching, and ideas of compositionality, our approach learns a hierarchy of spatially flexible compositions, i.e. parts, in an unsupervised, statistics-driven manner. Starting with simple, frequent features, we learn the statistically most significant compositions (parts composed of parts), which consequently define the next layer. Parts are learned sequentially, layer after layer, optimally adjusting to the visual data. Lower layers are learned in a category-independent way to obtain complex, yet sharable visual building blocks, which is a crucial step towards a scalable representation. Higher layers of the hierarchy, on the other hand, are constructed by using specific categories, achieving a category representation with a small number of highly generalizable parts that gained their structural flexibility through composition within the hierarchy. Built in this way, new categories can be efficiently and continuously added to the system by adding a small number of parts only in the higher layers. The approach is demonstrated on a large collection of images and a variety of object categories.

The Role of Context for Object Detection and Semantic Segmentation in the Wild

2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014

In this paper we study the role of context in existing stateof-the-art detection and segmentation... more In this paper we study the role of context in existing stateof-the-art detection and segmentation approaches. Towards this goal, we label every pixel of PASCAL VOC 2010 detection challenge with a semantic category. We believe this data will provide plenty of challenges to the community, as it contains 520 additional classes for semantic segmentation and object detection. Our analysis shows that nearest neighbor based approaches perform poorly on semantic segmentation of contextual classes, showing the variability of PASCAL imagery. Furthermore, improvements of existing contextual models for detection is rather modest. In order to push forward the performance in this difficult scenario, we propose a novel deformable part-based model, which exploits both local context around each candidate detection as well as global context at the level of the scene. We show that this contextual reasoning significantly helps in detecting objects at all scales.

Detect What You Can: Detecting and Representing Objects Using Holistic Models and Body Parts

2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014

Detecting objects becomes difficult when we need to deal with large shape deformation, occlusion ... more Detecting objects becomes difficult when we need to deal with large shape deformation, occlusion and low resolution. We propose a novel approach to i) handle large deformations and partial occlusions in animals (as examples of highly deformable objects), ii) describe them in terms of body parts, and iii) detect them when their body parts are hard to detect (e.g., animals depicted at low resolution). We represent the holistic object and body parts separately and use a fully connected model to arrange templates for the holistic object and body parts. Our model automatically decouples the holistic object or body parts from the model when they are hard to detect. This enables us to represent a large number of holistic object and body part combinations to better deal with different "detectability" patterns caused by deformations, occlusion and/or low resolution.

What Are You Talking About? Text-to-Image Coreference

2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014

In this paper we exploit natural sentential descriptions of RGB-D scenes in order to improve 3D s... more In this paper we exploit natural sentential descriptions of RGB-D scenes in order to improve 3D semantic parsing. Importantly, in doing so, we reason about which particular object each noun/pronoun is referring to in the image. This allows us to utilize visual information in order to disambiguate the so-called coreference resolution problem that arises in text. Towards this goal, we propose a structure prediction model that exploits potentials computed from text and RGB-D imagery to reason about the class of the 3D objects, the scene type, as well as to align the nouns/pronouns with the referred visual objects. We demonstrate the effectiveness of our approach on the challenging NYU-RGBD v2 dataset, which we enrich with natural lingual descriptions. We show that our approach significantly improves 3D detection and scene classification accuracy, and is able to reliably estimate the text-to-image alignment. Furthermore, by using textual and visual information, we are also able to successfully deal with coreference in text, improving upon the state-of-the-art Stanford coreference system .

Box in the Box: Joint 3D Layout and Object Reasoning from Single Images

2013 IEEE International Conference on Computer Vision, 2013

In this paper we propose an approach to jointly infer the room layout as well as the objects pres... more In this paper we propose an approach to jointly infer the room layout as well as the objects present in the scene. Towards this goal, we propose a branch and bound algorithm which is guaranteed to retrieve the global optimum of the joint problem. The main difficulty resides in taking into account occlusion in order to not over-count the evidence. We introduce a new decomposition method, which generalizes integral geometry to triangular shapes, and allows us to bound the different terms in constant time. We exploit both geometric cues and object detectors as image features and show large improvements in 2D and 3D object detection over state-of-the-art deformable part-based models.

Beat the MTurkers: Automatic Image Labeling from Weak 3D Supervision

2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014

Labeling large-scale datasets with very accurate object segmentations is an elaborate task that r... more Labeling large-scale datasets with very accurate object segmentations is an elaborate task that requires a high degree of quality control and a budget of tens or hundreds of thousands of dollars. Thus, developing solutions that can automatically perform the labeling given only weak supervision is key to reduce this cost. In this paper, we show how to exploit 3D information to automatically generate very accurate object segmentations given annotated 3D bounding boxes. We formulate the problem as the one of inference in a binary Markov random field which exploits appearance models, stereo and/or noisy point clouds, a repository of 3D CAD models as well as topological constraints. We demonstrate the effectiveness of our approach in the context of autonomous driving, and show that we can segment cars with the accuracy of 86% intersection-over-union, performing as well as highly recommended MTurkers!

Categorical Perception

by Sanja Fidler and Aleš Leonardis

Cognitive Systems Monographs, 2010

Page 1. 4 Categorical Perception Mario Fritz1, Mykhaylo Andriluka1, Sanja Fidler2, Michael Stark1... more

3D Object Detection with a Deformable 3D Cuboid Model

Supplementary material: A Sentence is Worth a Thousand Pixels

Supplementary Material: Analyzing Semantic Segmentation Using Hybrid Human-Machine CRFs

Describing the Scene as a Whole: Joint Object Detection

In this paper we propose an approach to holistic scene understanding that reasons jointly about r... more In this paper we propose an approach to holistic scene understanding that reasons jointly about regions, location, class and spatial extent of objects, presence of a class in the image, as well as the scene type. Learning and inference in our model are efficient as we reason at the segment level, and introduce auxiliary variables that allow us to decompose the inherent high-order potentials into pairwise potentials between a few variables with small number of states (at most the number of classes). Inference is done via a convergent message-passing algorithm, which, unlike graph-cuts inference, has no submodularity restrictions and does not require potential specific moves. We believe this is very important, as it allows us to encode our ideas and prior knowledge about the problem without the need to change the inference engine every time we introduce a new potential. Our approach outperforms the state-of-the-art on the MSRC-21 benchmark, while being much faster. Importantly, our holistic model is able to improve performance in all tasks.

Learning a hierarchical compositional shape vocabulary for multi-class object representation

Hierarchies allow feature sharing between objects at multiple levels of representation, can code ... more Hierarchies allow feature sharing between objects at multiple levels of representation, can code exponential variability in a very compact way and enable fast inference. This makes them potentially suitable for learning and recognizing a higher number of object classes. However, the success of the hierarchical approaches so far has been hindered by the use of hand-crafted features or predetermined grouping rules. This paper presents a novel framework for learning a hierarchical compositional shape vocabulary for representing multiple object classes. The approach takes simple contour fragments and learns their frequent spatial configurations. These are recursively combined into increasingly more complex and class-specific shape compositions, each exerting a high degree of shape variability. At the top-level of the vocabulary, the compositions are sufficiently large and complex to represent the whole shapes of the objects. We learn the vocabulary layer after layer, by gradually increasing the size of the window of analysis and reducing the spatial resolution at which the shape configurations are learned. The lower layers are learned jointly on images of all classes, whereas the higher layers of the vocabulary are learned incrementally, by presenting the algorithm with one object class after another. The experimental results show that the learned multi-class object representation scales favorably with the number of object classes and achieves a state-of-the-art detection performance at both, faster inference as well as shorter training times.

segDeepM: Exploiting Segmentation and Context in Deep Neural Networks for Object Detection

In this paper, we propose an approach that exploits object segmentation in order to improve the a... more In this paper, we propose an approach that exploits object segmentation in order to improve the accuracy of object detection. We frame the problem as inference in a Markov Random Field, in which each detection hypothesis scores object appearance as well as contextual information using Convolutional Neural Networks, and allows the hypothesis to choose and score a segment out of a large pool of accurate object segmentation proposals. This enables the detector to incorporate additional evidence when it is available and thus results in more accurate detections. Our experiments show an improvement of 4.1% in mAP over the R-CNN baseline on PASCAL VOC 2010, and 3.4% over the current state-of-the-art, demonstrating the power of our approach.

Visual semantic search: Retrieving videos via complex textual queries

In this paper, we tackle the problem of retrieving videos using complex natural language queries.... more In this paper, we tackle the problem of retrieving videos using complex natural language queries. Towards this goal, we first parse the sentential descriptions into a semantic graph, which is then matched to visual concepts using a generalized bipartite matching algorithm. Our approach exploits object appearance, motion and spatial relations, and learns the importance of each term using structure prediction. We demonstrate the effectiveness of our approach on a new dataset designed for semantic search in the context of autonomous driving, which exhibits complex and highly dynamic scenes with many objects. We show that our approach is able to locate a major portion of the objects described in the query with high accuracy, and improve the relevance in video retrieval.

Holistic scene understanding for 3d object detection with rgbd cameras

In this paper, we tackle the problem of indoor scene understanding using RGBD data. Towards this ... more In this paper, we tackle the problem of indoor scene understanding using RGBD data. Towards this goal, we propose a holistic approach that exploits 2D segmentation, 3D geometry, as well as contextual relations between scenes and objects. Specifically, we extend the CPMC [3] framework to 3D in order to generate candidate cuboids, and develop a conditional random field to integrate information from different sources to classify the cuboids. With this formulation, scene classification and 3D object recognition are coupled and can be jointly solved through probabilistic inference. We test the effectiveness of our approach on the challenging NYU v2 dataset. The experimental results demonstrate that through effective evidence integration and holistic reasoning, our approach achieves substantial improvement over the state-of-the-art.

$Figure 4. Comparison of different methods in cuboid detection. Performance measured in recall, i.e. the fraction of objects which are covered by at least one candidate cube (with overlap > 0.5.)$

Bottom-up Segmentation for Top-down Detection

In this paper we are interested in how semantic segmentation can help object detection. Towards t... more In this paper we are interested in how semantic segmentation can help object detection. Towards this goal, we propose a novel deformable part-based model which exploits region-based segmentation algorithms that compute candidate object regions by bottom-up clustering followed by ranking of those regions. Our approach allows every detection hypothesis to select a segment (including void), and scores each box in the image using both the traditional HOG filters as well as a set of novel segmentation features. Thus our model "blends" between the detector and segmentation models. Since our features can be computed very efficiently given the segments, we maintain the same complexity as the original DPM . We demonstrate the effectiveness of our approach in PASCAL VOC 2010, and show that when employing only a root filter our approach outperforms Dalal & Triggs detector [12] on all classes, achieving 13% higher average AP. When employing the parts, we outperform the original DPM in 19 out of 20 classes, achieving an improvement of 8% AP. Furthermore, we outperform the previous state-of-the-art on VOC'10 test by 4%.

Analyzing Semantic Segmentation Using Hybrid Human-Machine CRFs

2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013

Recent trends in semantic image segmentation have pushed for holistic scene understanding models ... more Recent trends in semantic image segmentation have pushed for holistic scene understanding models that jointly reason about various tasks such as object detection, scene recognition, shape analysis, contextual reasoning. In this work, we are interested in understanding the roles of these different tasks in aiding semantic segmentation. Towards this goal, we "plug-in" human subjects for each of the various components in a state-of-the-art conditional random field model (CRF) on the MSRC dataset. Comparisons among various hybrid human-machine CRFs give us indications of how much "head room" there is to improve segmentation by focusing research efforts on each of the tasks. One of the interesting findings from our slew of studies was that human classification of isolated super-pixels, while being worse than current machine classifiers, provides a significant boost in performance when plugged into the CRF! Fascinated by this finding, we conducted in depth analysis of the human generated potentials. This inspired a new machine potential which significantly improves state-of-the-art performance on the MRSC dataset.