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
Posted Content
An Image Classifier Can Suffice For Video Understanding.
TL;DR: In this paper, a new perspective on video understanding is proposed by casting the video recognition problem as an image recognition task, and the authors show that an image classifier alone can suffice for video understanding without temporal modeling.
Posted Content
EDDA: Explanation-driven Data Augmentation to Improve Model and Explanation Alignment.
TL;DR: In this article, an explanation-driven data augmentation (EDDA) method was proposed to improve alignment between model predictions and explanation methods. But the model and explainer alignment was not considered.
Journal ArticleDOI
Classification and localization of maize leaf spot disease based on weakly supervised learning
Shuai Yang,Ziyao Xing,Hengbin Wang,Xiang Gao,Xinrui Dong,Yung-Cheng Yao,Runda Zhang,Xiaodong Zhang,Shaoming Li,Yuanyuan Zhao,Zhe Liu +10 more
TL;DR: In this paper , a weakly supervised semantic segmentation based on class activation mapping techniques was used for identifying disease spots in maize leaf images, which achieved a mIoU of up to 55.302%.
Journal ArticleDOI
A Novel Confidence Induced Class Activation Mapping for MRI Brain Tumor Segmentation
TL;DR: Zhang et al. as mentioned in this paper proposed confidence-induced class activation mapping (Cfd-CAM), which calculates the weight of each feature map by using the confidence of the target class.
Journal ArticleDOI
Hybrid Domain Consistency Constraints-Based Deep Neural Network for Facial Expression Recognition
TL;DR: Zhang et al. as mentioned in this paper proposed a novel Hybrid Domain Consistency Network (HDCNet) based on a feature constraint method that combines both spatial domain consistency and channel domain consistency.
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.