Conference
Workshop on Applications of Computer Vision
About: Workshop on Applications of Computer Vision is an academic conference. The conference publishes majorly in the area(s): Feature extraction & Image segmentation. Over the lifetime, 2683 publications have been published by the conference receiving 84878 citations.
Topics: Feature extraction, Image segmentation, Object detection, Convolutional neural network, Segmentation
Papers published on a yearly basis
Papers
More filters
05 Dec 1994
TL;DR: This paper presents a set of experimental results in which various HMM parameterisations are analysed and shows that stochastic modelling can be used successfully to encode feature information.
Abstract: Recent work on face identification using continuous density Hidden Markov Models (HMMs) has shown that stochastic modelling can be used successfully to encode feature information. When frontal images of faces are sampled using top-bottom scanning, there is a natural order in which the features appear and this can be conveniently modelled using a top-bottom HMM. However, a top-bottom HMM is characterised by different parameters, the choice of which has so far been based on subjective intuition. This paper presents a set of experimental results in which various HMM parameterisations are analysed. >
2,677 citations
24 Mar 2017
TL;DR: A new method for setting the learning rate, named cyclical learning rates, is described, which practically eliminates the need to experimentally find the best values and schedule for the global learning rates.
Abstract: It is known that the learning rate is the most important hyper-parameter to tune for training deep neural networks. This paper describes a new method for setting the learning rate, named cyclical learning rates, which practically eliminates the need to experimentally find the best values and schedule for the global learning rates. Instead of monotonically decreasing the learning rate, this method lets the learning rate cyclically vary between reasonable boundary values. Training with cyclical learning rates instead of fixed values achieves improved classification accuracy without a need to tune and often in fewer iterations. This paper also describes a simple way to estimate "reasonable bounds" – linearly increasing the learning rate of the network for a few epochs. In addition, cyclical learning rates are demonstrated on the CIFAR-10 and CIFAR-100 datasets with ResNets, Stochastic Depth networks, and DenseNets, and the ImageNet dataset with the AlexNet and GoogLeNet architectures. These are practical tools for everyone who trains neural networks.
1,521 citations
12 Mar 2018
TL;DR: This paper proposes Grad-CAM++, which uses a weighted combination of the positive partial derivatives of the last convolutional layer feature maps with respect to a specific class score as weights to generate a visual explanation for the class label under consideration, to provide better visual explanations of CNN model predictions.
Abstract: Over the last decade, Convolutional Neural Network (CNN) models have been highly successful in solving complex vision based problems. However, deep models are perceived as "black box" methods considering the lack of understanding of their internal functioning. There has been a significant recent interest to develop explainable deep learning models, and this paper is an effort in this direction. Building on a recently proposed method called Grad-CAM, we propose Grad-CAM++ to provide better visual explanations of CNN model predictions (when compared to Grad-CAM), in terms of better localization of objects as well as explaining occurrences of multiple objects of a class in a single image. We provide a mathematical explanation for the proposed method, Grad-CAM++, which uses a weighted combination of the positive partial derivatives of the last convolutional layer feature maps with respect to a specific class score as weights to generate a visual explanation for the class label under consideration. Our extensive experiments and evaluations, both subjective and objective, on standard datasets showed that Grad-CAM++ indeed provides better visual explanations for a given CNN architecture when compared to Grad-CAM.
1,451 citations
12 Mar 2018
TL;DR: DUC is designed to generate pixel-level prediction, which is able to capture and decode more detailed information that is generally missing in bilinear upsampling, and a hybrid dilated convolution (HDC) framework in the encoding phase is proposed.
Abstract: Recent advances in deep learning, especially deep convolutional neural networks (CNNs), have led to significant improvement over previous semantic segmentation systems. Here we show how to improve pixel-wise semantic segmentation by manipulating convolution-related operations that are of both theoretical and practical value. First, we design dense upsampling convolution (DUC) to generate pixel-level prediction, which is able to capture and decode more detailed information that is generally missing in bilinear upsampling. Second, we propose a hybrid dilated convolution (HDC) framework in the encoding phase. This framework 1) effectively enlarges the receptive fields (RF) of the network to aggregate global information; 2) alleviates what we call the "gridding issue"caused by the standard dilated convolution operation. We evaluate our approaches thoroughly on the Cityscapes dataset, and achieve a state-of-art result of 80.1% mIOU in the test set at the time of submission. We also have achieved state-of-theart overall on the KITTI road estimation benchmark and the PASCAL VOC2012 segmentation task. Our source code can be found at https://github.com/TuSimple/TuSimple-DUC.
1,358 citations
19 Oct 1998
TL;DR: An end-to-end method for extracting moving targets from a real-time video stream, classifying them into predefined categories according to image-based properties, and then robustly tracking them is described.
Abstract: This paper describes an end-to-end method for extracting moving targets from a real-time video stream, classifying them into predefined categories according to image-based properties, and then robustly tracking them. Moving targets are detected using the pixel wise difference between consecutive image frames. A classification metric is applied these targets with a temporal consistency constraint to classify them into three categories: human, vehicle or background clutter. Once classified targets are tracked by a combination of temporal differencing and template matching. The resulting system robustly identifies targets of interest, rejects background clutter and continually tracks over large distances and periods of time despite occlusions, appearance changes and cessation of target motion.
1,278 citations