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
Recursive Visual Explanations Mediation Scheme Based on DropAttention Model With Multiple Episodes Pool
TL;DR: In this article , a new scheme of mediating the visual explanations in a pixel-level recursively is proposed, which generates multiple episodes pool by training only a single network once as an amortized model, which shows stability on task performance regardless of layer-wise attention policy.
Journal ArticleDOI
Rethinking Gradient Weight’s Influence over Saliency Map Estimation
TL;DR: A global guidance map is used to rectify the weighted aggregation operation during saliency estimation, where resultant interpretations are comparatively cleaner and instance-specific.
Journal ArticleDOI
The role of artificial intelligence in the differential diagnosis of wheezing symptoms in children
TL;DR: In this article , a review aims to comprehensively assess these studies in this field, analyze their interpretability and limitations, and explore and discuss future research directions in real-world clinical applications.
Proceedings ArticleDOI
Rethinking of Domain Users Control in Computer Vision Pipelines by Customized Attention
TL;DR: In this paper , a Visual Interpretation-based Control (VIC) technique is proposed to enable non-experts to dictate their intuition from the most important areas in an image and incorporate this within CV pipelines.
Feature Activation Map: Visual Explanation of Deep Learning Models for Image Classification
TL;DR: Wang et al. as mentioned in this paper proposed a post-hoc interpretation tool named feature activation map (FAM), which can interpret deep learning models without FC layers as a classifier.
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.