DISCOVER: Making Vision Networks Interpretable via Competition and Dissection

7 October 2023

Papers citing "DISCOVER: Making Vision Networks Interpretable via Competition and Dissection"

6 / 6 papers shown

Title
Discovering Influential Neuron Path in Vision Transformers Yifan Wang Yifei Liu Yingdong Shi Chong Li Anqi Pang Sibei Yang Jingyi Yu Kan Ren ViT 69 0 0 12 Mar 2025
Coarse-to-Fine Concept Bottleneck Models Konstantinos P. Panousis Dino Ienco Diego Marcos 25 5 0 03 Oct 2023
Sparse Linear Concept Discovery Models Konstantinos P. Panousis Dino Ienco Diego Marcos 28 15 0 21 Aug 2023
Natural Language Descriptions of Deep Visual Features Evan Hernandez Sarah Schwettmann David Bau Teona Bagashvili Antonio Torralba Jacob Andreas MILM 201 117 0 26 Jan 2022
Stochastic Local Winner-Takes-All Networks Enable Profound Adversarial Robustness Konstantinos P. Panousis S. Chatzis Sergios Theodoridis BDL AAML 60 11 0 05 Dec 2021
Local Competition and Stochasticity for Adversarial Robustness in Deep Learning Konstantinos P. Panousis S. Chatzis Antonios Alexos Sergios Theodoridis BDL AAML OOD 56 19 0 04 Jan 2021