Papers by Joao Paulo Schwarz Schuler
K-CAI NEURAL API v0.1.6
<strong>K-CAI NEURAL API</strong> is a Keras based neural network API that will allow... more <strong>K-CAI NEURAL API</strong> is a Keras based neural network API that will allow you to prototype faster! From version v0.1.6, the new function <strong>cai.datasets.save_tfds_in_format</strong> saves a TensorFlow dataset as image files. Classes become folders for easy of use by standard Keras API.
Inteligência artificial popperiana
Frontiers in Artificial Intelligence and Applications, 2021
The Food and Agriculture Organization (FAO) estimated that plant diseases cost the world economy ... more The Food and Agriculture Organization (FAO) estimated that plant diseases cost the world economy $220 billion in 2019. In this paper, we propose a lightweight Deep Convolutional Neural Network (DCNN) for automatic and reliable plant leaf diseases classification. The proposed method starts by converting input images of plant leaves from RGB to CIE LAB coordinates. Then, L and AB channels go into separate branches along with the first three layers of a modified Inception V3 architecture. This approach saves from 1/3 to 1/2 of the parameters in the separated branches. It also provides better classification reliability when perturbing the original RGB images with several types of noise (salt and pepper, blurring, motion blurring and occlusions). These types of noise simulate common image variability found in the natural environment. We hypothesize that the filters in the AB branch provide better resistance to these types of variability due to their relatively low frequency in the image-...
Frontiers in Artificial Intelligence and Applications, 2021
EfficientNet is a recent Deep Convolutional Neural Network (DCNN) architecture intended to be pro... more EfficientNet is a recent Deep Convolutional Neural Network (DCNN) architecture intended to be proportionally extendible in depth, width and resolution. Through its variants, it can achieve state of the art accuracy on the ImageNet classification task as well as on other classical challenges. Although its name refers to its efficiency with respect to the ratio between outcome (accuracy) and needed resources (number of parameters, flops), we are studying a method to reduce the original number of trainable parameters by more than 84% while keeping a very similar degree of accuracy. Our proposal is to improve the pointwise (1x1) convolutions, whose number of parameters rapidly grows due to the multiplication of the number of filters by the number of input channels that come from the previous layer. Basically, our tweak consists in grouping filters into parallel branches, where each branch processes a fraction of the input channels. However, by doing so, the learning capability of the DC...
Uploads
Papers by Joao Paulo Schwarz Schuler