Joint learning for multi-class object detection
Quoc-cuong Pham2014, 2014 International Conference on Computer Vision Theory and Applications (VISAPP)
Sign up for access to the world's latest research
checkGet notified about relevant papers
checkSave papers to use in your research
checkJoin the discussion with peers
checkTrack your impact
Abstract
In practice, multiple objects in images are located by consecutively applying one detector for each class and taking the best confident score. In this work, we propose to show the advantage of grouping similar object classes into a hierarchical structure. While this approach has found interest in image classification, it is not analyzed for the object detection task. Each node in the hierarchy represents one decision line. All the decision lines are learned jointly using a novel problem formulation. Based on experiments using PASCAL VOC 2007 dataset, we show that our approach improves detection performance compared to a baseline approach.
Related papers
Evaluating multi-class learning strategies in a hierarchical framework for object detection
Multi-class object learning and detection is a challenging problem due to the large number of object classes and their high visual variability. Specialized detectors usually excel in performance, while joint representations optimize sharing and reduce inference time -but are complex to train. Conveniently, sequential class learning cuts down training time by transferring existing knowledge to novel classes, but cannot fully exploit the shareability of features among object classes and might depend on ordering of classes during learning. In hierarchical frameworks these issues have been little explored. In this paper, we provide a rigorous experimental analysis of various multiple object class learning strategies within a generative hierarchical framework. Specifically, we propose, evaluate and compare three important types of multi-class learning: 1.) independent training of individual categories, 2.) joint training of classes, and 3.) sequential learning of classes. We explore and compare their computational behavior (space and time) and detection performance as a function of the number of learned object classes on several recognition datasets. We show that sequential training achieves the best trade-off between inference and training times at a comparable detection performance and could thus be used to learn the classes on a larger scale.
An Efficient Shared Multi-Class Detection Cascade
Procedings of the British Machine Vision Conference 2008, 2008
We propose a novel multi-class object detector, that optimizes the detection costs while retaining a desired detection rate. The detector uses a cascade that unites the handling of similar object classes while separating off classes at appropriate levels of the cascade. No prior knowledge about the relationship between classes is needed as the classifier structure is automatically determined during the training phase. The detection nodes in the cascade use Haar wavelet features and Gentle AdaBoost, however the approach is not dependent on the specific features used and can easily be extended to other cases. Experiments are presented for several numbers of object classes and the approach is compared to other classifying schemes. The results demonstrate a large efficiency gain that is particularly prominent for a greater number of classes. Also the complexity of the training scales well with the number of classes.
Efficient, Simultaneous Detection of Multiple Object Classes
18th International Conference on Pattern Recognition (ICPR'06), 2006
At present, the object categorisation literature is still dominated by the use of individual class detectors. Detecting multiple classes then implies the subsequent application of multiple such detectors, but such an approach is not scalable towards high numbers of classes. This paper presents an alternative strategy, where multiple classes are detected in a combined way. This includes a decision tree approach, where ternary rather than binary nodes are used, and where nodes share features. This yields an efficient scheme, which scales much better. The paper proposes a strategy where the object samples are first distinguished from the background. Then, in a second stage, the actual object class membership of each sample is determined. The focus of the paper lies entirely on the first stage, i.e. the distinction from background. The tree approach for this step is compared against two alternative strategies, one of them being the popular cascade approach. While classification accuracy tends to be better or comparable, the speed of the proposed method is systematically better. This advantage gets more outspoken as the number of object classes increases. easy exemplars easy exemplars difficult exemplars
Evaluating multi-class learning strategies in a generative hierarchical framework for object detection
Multi-class object learning and detection is a challenging problem due to the large number of object classes and their high visual variability. Specialized de- tectors usually excel in performance, while joint representations optimize sharing and reduce inference time — but are complex to train. Conveniently, sequential class learning cuts down training time by transferring existing knowledge to novel classes, but cannot fully exploit the shareability of features among object classes and might depend on ordering of classes during learning. In hierarchical frame- works these issues have been little explored. In this paper, we provide a rigorous experimental analysis of various multiple object class learning strategies within a generative hierarchical framework. Specifically, we propose, evaluate and com- pare three important types of multi-class learning: 1.) independent training of individual categories, 2.) joint training of classes, and 3.) sequential learning of classes. We explo...
Learning to Detect Objects of Many Classes Using Binary Classifiers
Viola and Jones [VJ] demonstrate that cascade classification methods can successfully detect objects belonging to a single class, such as faces. Detecting and identifying objects that belong to any of a set of "classes", many class detection, is a much more challenging problem. We show that objects from each class can form a "cluster" in a "classifier space" and illustrate examples of such clusters using images of real world objects. Our detection algorithm uses a "decision tree classifier" (whose internal nodes each correspond to a VJ classifier) to propose a class label for every sub-image W of a test image (or reject it as a negative instance). If this W reaches a leaf of this tree, we then pass W through a subsequent VJ cascade of classifiers, specific to the identified class, to determine whether W is truly an instance of the proposed class. We perform several empirical studies to compare our system for detecting objects of any of M classes, to the obvious approach of running a set of M learned VJ cascade classifiers, one for each class of objects, on the same image. We found that the detection rates are comparable, and our many-class detection system is about as fast as running a single VJ cascade, and scales up well as the number of classes increases.
Performance Analysis of Different Optimization Algorithms for Multi-Class Object Detection
International Journal on Recent and Innovation Trends in Computing and Communication
Object recognition is a significant approach employed for recognizing suitable objects from the image. Various improvements, particularly in computer vision, are probable to diagnose highly difficult tasks with the assistance of local feature detection methodologies. Detecting multi-class objects is quite challenging, and many existing researches have worked to enhance the overall accuracy. But because of certain limitations like higher network loss, degraded training ability, improper consideration of features, less convergent and so on. The proposed research introduced a hybrid convolutional neural network (H-CNN) approach to overcome these drawbacks. The collected input images are pre-processed initially through Gaussian filtering to eradicate the noise and enhance the image quality. Followed by image pre-processing, the objects present in the images are localized using Grid Guided Localization (GGL). The effective features are extracted from the localized objects using the AlexN...
TCAS: A multiclass object detector for robot and computer vision applications
Building efficient object detection systems is an important goal of computer and robot vision. If several object types are to be detected, the most simple solution is to run several object-specific classifiers independently of each other (in parallel). This solution is computationally expensive if several object classes are to be detected. In this paper, TCAS, a new classifier structure designed to be used on multiclass object detection problems is introduced as an alternative solution. TCAS offers an efficient solution and reduces the aggregated false detection rate. TCAS extends cascade classifiers (introduced by Viola & Jones) to the multiclass case and corresponds to a nested coarse-to-fine tree of multiclass nested boosted cascades. Results for three different object detection problems are presented: face and hand detection, robot detection, and multiview face detection. In the experiments, the obtained TCAS have classification times about 2-times shorter than the ones obtained using parallel cascades, and have the same or lower number of false positives (for the same detection rate).
Coarse-To-Fine Multiclass Nested Cascades for Object Detection
2010
Building robust and fast object detection systems is an important goal of computer vision. A problem arises when several object types are to be detected, because the computational burden of running several specific classifiers in parallel becomes a problem. In addition the accuracy and the training time can be greatly affected. Seeking to provide a solution to these problems, we extend cascade classifiers to the multiclass case by proposing the use of multiclass coarse-tofine (CTF) nested cascades. The presented results show that the proposed system scales well with the number of classes, both at training and running time.
Learning Object Detection using Multiple Neural Networks
Multiple neural network systems have become popular techniques for tackling complex tasks, often giving improved performance compared to a single network. In this study we propose an innovative detection algorithm in image analysis using a multiple neural network approach where many neural networks are jointly used to solve the object detection problem. We use a group of networks configured with different parameters and features, then combines them in order to obtain new networks. The topology of the set of neural networks is statically configured as a tree where the root node produces in output the detection map. This work represents a preliminary study through which we want to move from detection to segmentation and recognition of objects of interest. We have compared our model with other detection algorithms using a standard dataset and the results are encouraging. The results highlight the advantages and problems that will guide the evolution of the proposed model.
Learning a Family of Detectors
2009
Object detection and recognition are important problems in computer vision. The challenges of these problems come from the presence of noise, background clutter, large within class variations of the object class and limited training data. In addition, the computational complexity in the recognition process is also a concern in practice. In this thesis, we propose one approach to handle the problem of detecting an object class that exhibits large within-class variations, and a second approach to speed up the classification processes.
Learning Object Detection using Multiple Neural Netwoks
Multiple neural network systems have become popular techniques for tackling complex tasks, often giving improved performance compared to a single network. In this study we propose an innovative detection algorithm in image analysis using a multiple neural network approach where many neural networks are jointly used to solve the object detection problem. We use a group of networks configured with different parameters and features, then combines them in order to obtain new networks. The topology of the set of neural networks is statically configured as a tree where the root node produces in output the detection map. This work represents a preliminary study through which we want to move from detection to segmentation and recognition of objects of interest. We have compared our model with other detection algorithms using a standard dataset and the results are encouraging. The results highlight the advantages and problems that will guide the evolution of the proposed model.
Toward an Ensemble of Object Detectors
2020
The field of object detection has witnessed great strides in recent years. With the wave of deep neural networks (DNN), many breakthroughs have achieved for the problems of object detection which previously were thought to be difficult. However, there exists a limitation with DNN-based approaches as some architectures are only suitable for particular types of object. Thus it would be desirable to combine the strengths of different methods to handle objects in different contexts. In this study, we propose an ensemble of object detectors in which individual detectors are adaptively combine for the collaborated decision. The combination is conducted on the outputs of detectors including the predicted label and location for each object. We proposed a detector selection method to select the suitable detectors and a weighted-based combining method to combine the predicted locations of selected detectors. The parameters of these methods are optimized by using Particle Swarm Optimization in order to maximize mean Average Precision (mAP) metric. Experiments conducted on VOC2007 dataset with six object detectors show that our ensemble method is better than each single detector.
Multiple Object Detection using Deep Neural Networks
In this paper, we present a system for the detection of multiple objects in an image. The system takes scenes as input, and outputs a set of objects present in the scene. The system first generates and analyses region proposals using deep convolutional neural networks. Next, a postprocessing algorithm exploits temporal information between consecutive frames to enhance the overall confidence of a detected object. The system can be extended to be used in other domains as well.
Multiple component learning for object detection
2008
Object detection is one of the key problems in computer vision. In the last decade, discriminative learning approaches have proven effective in detecting rigid objects, achieving very low false positives rates. The field has also seen a resurgence of part-based recognition methods, with impressive results on highly articulated, diverse object categories. In this paper we propose a discriminative learning approach for detection that is inspired by part-based recognition approaches.
Hybrid Parallel Cascade Classifier Training for Object Detection
Lecture Notes in Computer Science, 2014
A drawback of the Viola and Jones framework for object detection in digital images is the large amount of time needed to train the underlying cascade classifiers. In this paper, we propose a novel hybrid approach for parallelizing that framework. The approach employs message passing among computers and multi-threading in the processor cores, hence its hybrid nature. In contrast to related works, which dealt with only parts the original framework, in this paper we considered the complete framework. Besides, the set of weak classifiers obtained by our parallel approach is identical to the one of a serial version. An experimental evaluation on face detection focused on speedup and scalability measures and has shown the improvements of the proposed approach over a serial implementation of the original framework.
Rapid Detection of Many Object Instances
Advanced Concepts for Intelligent …, 2009
Segmentation-based multi-class semantic object detection
Multimedia Tools and Applications, 2012
In this paper we study the problem of the detection of semantic objects from known categories in images. Unlike existing techniques which operate at the pixel or at a patch level for recognition, we propose to rely on the categorization of image segments. Recent work has highlighted that image segments provide a sound support for visual object class recognition. In this work, we use image segments as primitives to extract robust features and train detection models for a predefined set of categories. Several segmentation algorithms are benchmarked and their performances for segment recognition are compared. We then propose two methods for enhancing the segments classification, one based on the fusion of the classification results obtained with the different segmentations, the other one based on the optimization of the global labelling by correcting local ambiguities between neighbor segments. We use as a benchmark the Microsoft MSRC-21 image database and show that our method competes with the current state-of-the-art.
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014
Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that typically combine multiple low-level image features with high-level context. In this paper, we propose a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012-achieving a mAP of 53.3%. Our approach combines two key insights:
Progress in multi-object detection models: a comprehensive survey
Deep learning-based object detection has become popular due to its strong learning ability and advantages in dealing with occlusion, scale transformation, and context changes. In recent years, it has become a research hotspot. This paper presents the current Deep Learning models from Generic and Salient detection models ranging from one-stage to two-stage for multi-object detection in various applications. Nevertheless, we also examined the advantages and some drawbacks of those models. Furthermore, challenges such as variation in object scales, computation time, illumination differing from various applications, and promising research directions of Deep Learning models are discussed. Finally, we proposed Dense PRediction Simplified (DPRS) based on the YOLO model. Backbones play a vital role in enhancing the performance of detection models, and efficient Backbone architecture will be fused to achieve the competitive state-of-art result.
A Hierarchical Methodology for Class Detection Problems with Skewed Priors
Journal of Classification, 2005
We describe a novel extension to the Class-Cover-Catch-Digraph (CCCD) classifier, specifically tuned to detection problems. These are two-class classification problems where the natural priors on the classes are skewed by several orders of magnitude. The emphasis of the proposed techniques is in computationally efficient classification for real-time applications. Our principal contribution consists of two boosted classifiers built upon the CCCD structure, one in the form of a sequential decision process and the other in the form of a tree. Both of these classifiers achieve performances comparable to that of the original CCCD classifiers, but at drastically reduced computational expense. An analysis of classification performance and computational cost is performed using data from a face detection application. Comparisons are provided with Support Vector Machines (SVM) and reduced SVMs. These comparisons show that while some SVMs may achieve higher classification performance, their computational burden can be so high as to make them unusable in real-time applications. On the other hand, the proposed classifiers combine high detection performance with extremely fast classification.
Related topics
Loading Preview
Sorry, preview is currently unavailable. You can download the paper by clicking the button above.