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
VS-CAM: Vertex Semantic Class Activation Mapping to Interpret Vision Graph Neural Network
TL;DR: Qualitative results show that VS-CAM can obtain heatmaps where the highlighted regions match the objects much more precisely than CNN-based CAM, and quantitative evaluation further demonstrates the superiority of VS- CAM.
Posted Content
Keep CALM and Improve Visual Feature Attribution
TL;DR: CALM as mentioned in this paper improves CAM by explicitly incorporating a latent variable encoding the location of the cue for recognition in the formulation, thereby subsuming the attribution map into the training computational graph.
Journal ArticleDOI
Thermal conductivity prediction of UO2-BeO composite fuels and related decisive features discovery via convolutional neural network
Zhanpeng Gong,XU Zhixuan,Jinlong Hu,Biaojie Yan,Xiangdong Ding,Jun Sun,Feng Zhang,Junkai Deng +7 more
TL;DR: In this article , the authors investigated the relationship between the thermal conductivity (TC) of the UO2/BeO composite and their corresponding microstructures by using a convolutional neural network (CNN).
Proceedings ArticleDOI
Improving Explainability of Integrated Gradients with Guided Non-Linearity
TL;DR: In this paper, a guided nonlinearity is proposed to propagate gradients more effectively through non-linear units (e.g., ReLU and max-pool) so that only positive gradients backpropagate through nonlinear units.
Posted Content
PACE: Posthoc Architecture-Agnostic Concept Extractor for Explaining CNNs
TL;DR: In this paper, a post-hoc architecture-agnostic concept extractor (PACE) is proposed to automatically extract smaller sub-regions of the image called concepts relevant to the black-box prediction.
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.