B-cos Alignment for Inherently Interpretable CNNs and Vision
Transformers

B-cos Alignment for Inherently Interpretable CNNs and Vision Transformers

19 June 2023

Moritz D Boehle

Navdeeppal Singh

Mario Fritz

Bernt Schiele

Papers citing "B-cos Alignment for Inherently Interpretable CNNs and Vision Transformers"

7 / 7 papers shown

Title
Disentangling Visual Transformers: Patch-level Interpretability for Image Classification Guillaume Jeanneret Loïc Simon F. Jurie ViT 44 0 0 24 Feb 2025
B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable Shreyash Arya Sukrut Rao Moritz Bohle Bernt Schiele 63 2 0 28 Jan 2025
COMIX: Compositional Explanations using Prototypes S. Sivaprasad D. Kangin Plamen Angelov Mario Fritz 56 0 0 10 Jan 2025
Benchmarking the Attribution Quality of Vision Models Robin Hesse Simone Schaub-Meyer Stefan Roth FAtt 21 3 0 16 Jul 2024
High-Performance Large-Scale Image Recognition Without Normalization Andrew Brock Soham De Samuel L. Smith Karen Simonyan VLM 220 510 0 11 Feb 2021
Aggregated Residual Transformations for Deep Neural Networks Saining Xie Ross B. Girshick Piotr Dollár Z. Tu Kaiming He 261 10,106 0 16 Nov 2016
Densely Connected Convolutional Networks Gao Huang Zhuang Liu L. V. D. van der Maaten Kilian Q. Weinberger PINN 3DV 244 35,884 0 25 Aug 2016