Proceedings ArticleDOI
Ablation-CAM: Visual Explanations for Deep Convolutional Network via Gradient-free Localization
Saurabh Desai,Harish G. Ramaswamy +1 more
- pp 983-991
TLDR
This approach – Ablation-based Class Activation Mapping (Ablation CAM) uses ablation analysis to determine the importance of individual feature map units w.r.t. class to produce a coarse localization map highlighting the important regions in the image for predicting the concept.Abstract:
In response to recent criticism of gradient-based visualization techniques, we propose a new methodology to generate visual explanations for deep Convolutional Neural Networks (CNN) - based models. Our approach – Ablation-based Class Activation Mapping (Ablation CAM) uses ablation analysis to determine the importance (weights) of individual feature map units w.r.t. class. Further, this is used to produce a coarse localization map highlighting the important regions in the image for predicting the concept. Our objective and subjective evaluations show that this gradient-free approach works better than state-of-the-art Grad-CAM technique. Moreover, further experiments are carried out to show that Ablation-CAM is class discriminative as well as can be used to evaluate trust in a model.read more
Citations
More filters
Journal ArticleDOI
Classification and visual explanation for COVID-19 pneumonia from CT images using triple learning
Sota Kato,Masahiro Okuda,Kensaku Mori,Akinobu Shimizu,Yoshito Otake,Masahiro Hashimoto,Toshiaki Akashi,Kazuhiro Hotta +7 more
TL;DR: In this paper , a novel framework for classifying and visualizing pneumonia induced by COVID-19 from CT images is presented, which uses contrastive learning and an attention mechanism.
Journal ArticleDOI
A Novel Image Classification Method Based on Residual Network, Inception, and Proposed Activation Function
TL;DR: In this paper , the authors replace skip connections and Relu with non-monotonic activation function (NMAF) to reduce the parameter number of ResNet by around 6 M parameters and reduce the run time by 30 s/epoch.
Journal ArticleDOI
Teaching AI to Teach: Leveraging Limited Human Salience Data Into Unlimited Saliency-Based Training
TL;DR: In this article , a teacher-student training paradigm was proposed to augment a small amount of human annotations to generate salience maps for an arbitrary amount of additional training data, which can be used to supplement a limited number of human-provided annotations with an arbitrarily large number of model-generated image annotations.
Journal ArticleDOI
Towards Query Efficient Black-Box Attacks: A Universal Dual Transferability-Based Framework
TL;DR: Zhang et al. as discussed by the authors proposed a dual transferability (DT) based black-box attack framework to perturb the discriminative areas of clean examples within limited queries.
Journal ArticleDOI
Denoising by Decorated Noise: An Interpretability-Based Framework for Adversarial Example Detection
TL;DR: Zhang et al. as discussed by the authors proposed a novel framework to filter out the adversarial perturbations by superimposing the original images with the noises decorated by a new gradient-independent visualization method, namely, score class activation map (Score-CAM).
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Proceedings ArticleDOI
Going deeper with convolutions
Christian Szegedy,Wei Liu,Yangqing Jia,Pierre Sermanet,Scott Reed,Dragomir Anguelov,Dumitru Erhan,Vincent Vanhoucke,Andrew Rabinovich +8 more
TL;DR: Inception as mentioned in this paper is a deep convolutional neural network architecture that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).
Proceedings ArticleDOI
Fully convolutional networks for semantic segmentation
TL;DR: The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning.