Towards Improved Input Masking for Convolutional Neural Networks

v1v2v3 (latest)

Towards Improved Input Masking for Convolutional Neural Networks

IEEE International Conference on Computer Vision (ICCV), 2022

26 November 2022

S. Balasubramanian

ArXiv (abs)PDF HTML HuggingFace (1 upvotes)Github (5★)

Papers citing "Towards Improved Input Masking for Convolutional Neural Networks"

4 / 4 papers shown

Title
Detecting Regional Spurious Correlations in Vision Transformers via Token Discarding Solha Kang Esla Timothy Anzaku W. D. Neve Arnout Van Messem J. Vankerschaver Francois Rameau Utku Ozbulak ViT 150 0 0 04 Sep 2025
Towards Human-Understandable Multi-Dimensional Concept DiscoveryComputer Vision and Pattern Recognition (CVPR), 2025 Arne Grobrugge Niklas Kühl G. Satzger Philipp Spitzer 246 2 0 24 Mar 2025
Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP S. Balasubramanian Samyadeep Basu Soheil Feizi CLIP 246 14 0 03 Jun 2024
"Why Should I Trust You?": Explaining the Predictions of Any Classifier Marco Tulio Ribeiro Sameer Singh Carlos Guestrin FAtt FaML 2.3K 19,543 0 16 Feb 2016