Collection-CAM: A Faster Region-Based Saliency Method Using Collection-Wise Mask Over Pyramidal Features
Due to the black-box nature of deep networks, making explanations of their decision-making is extremely challenging. A solution is using post-hoc attention mechanisms with the deep network to verify the decision basis. However, those methods have problems such as gradient noise and false confidence....
Main Authors: | Yungi Ha, Chan-Hyun Youn |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2022-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9924199/ |
Similar Items
-
Federated Onboard-Ground Station Computing With Weakly Supervised Cascading Pyramid Attention Network for Satellite Image Analysis
by: Taewoo Kim, et al.
Published: (2022-01-01) -
Explaining CNN and RNN Using Selective Layer-Wise Relevance Propagation
by: Yeon-Jee Jung, et al.
Published: (2021-01-01) -
From heatmaps to structured explanations of image classifiers
by: Li Fuxin, et al.
Published: (2021-12-01) -
SDA-Vis: A Visualization System for Student Dropout Analysis Based on Counterfactual Exploration
by: Germain Garcia-Zanabria, et al.
Published: (2022-06-01) -
Collective ion acceleration/
by: 271517 Olson, C. L.
Published: (1979)