B-cos Networks: Alignment is All We Need for Interpretability-Reference-Cited by-同舟云学术

B-cos Networks: Alignment is All We Need for Interpretability

Published:2022-06 Issue: Volume: Page:
ISSN:
Container-title:2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
language:
Short-container-title:

Author:

Bohle Moritz¹,Fritz Mario¹,Schiele Bernt²

Affiliation:

1. MPI for Informatics, Saarland Informatics Campus

2. CISPA Helmholtz Center for Information Security

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/9878378/9878366/09879849.pdf?arnumber=9879849

Reference45 articles.

1. Rethinking the Inception Architecture for Computer Vision

2. Axiomatic Attribution for Deep Networks;sundararajan;International Conference on Machine Learning (ICML),0

3. Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps;simonyan;International Conference on Learning Representations (ICLR),0

4. Learning Important Features Through Propagating Activation Differences;shrikumar;International Conference on Machine Learning (ICML),0

5. Do Input Gradients Highlight Discriminative Features?;shah;CoRR,2021

Cited by 24 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Towards Explaining Hypercomplex Neural Networks;2024 International Joint Conference on Neural Networks (IJCNN);2024-06-30

2. Transparent Projection Networks for Interpretable Image Recognition;2024 International Joint Conference on Neural Networks (IJCNN);2024-06-30

3. B-Cos Alignment for Inherently Interpretable CNNs and Vision Transformers;IEEE Transactions on Pattern Analysis and Machine Intelligence;2024-06

4. Finding Component Relationships: A Deep-Learning-Based Anomaly Detection Interpreter;IEEE Transactions on Computational Social Systems;2024-06

5. Optimizing the Learning Process with Limited Computational Resources;2024 XXVII International Conference on Soft Computing and Measurements (SCM);2024-05-22