From Hope to Safety: Unlearning Biases of Deep Models via Gradient
Penalization in Latent Space

From Hope to Safety: Unlearning Biases of Deep Models via Gradient Penalization in Latent Space

18 August 2023

Maximilian Dreyer

Christopher J. Anders

Sebastian Lapuschkin

Papers citing "From Hope to Safety: Unlearning Biases of Deep Models via Gradient Penalization in Latent Space"

12 / 12 papers shown

Title
Investigating the Relationship Between Debiasing and Artifact Removal using Saliency Maps Lukasz Sztukiewicz Ignacy Stepka Michał Wiliński Jerzy Stefanowski 104 0 0 28 Feb 2025
Concept-level Debugging of Part-Prototype Networks A. Bontempelli Stefano Teso Katya Tentori Fausto Giunchiglia Andrea Passerini 48 53 0 31 May 2022
Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence Frederik Pahde Maximilian Dreyer Leander Weber Moritz Weckbecker Christopher J. Anders Thomas Wiegand Wojciech Samek Sebastian Lapuschkin 100 9 0 07 Feb 2022
Can contrastive learning avoid shortcut solutions? Joshua Robinson Li Sun Ke Yu Kayhan Batmanghelich Stefanie Jegelka S. Sra SSL 55 143 0 21 Jun 2021
Finding and Fixing Spurious Patterns with Explanations Gregory Plumb Marco Tulio Ribeiro Ameet Talwalkar 60 41 0 03 Jun 2021
Causally motivated Shortcut Removal Using Auxiliary Labels Maggie Makar Ben Packer D. Moldovan Davis W. Blalock Yoni Halpern Alexander DÁmour OOD CML 56 72 0 13 May 2021
Interpretations are useful: penalizing explanations to align neural networks with prior knowledge Laura Rieger Chandan Singh W. James Murdoch Bin Yu FAtt 68 213 0 30 Sep 2019
BCN20000: Dermoscopic Lesions in the Wild Marc Combalia Noel Codella V. Rotemberg Brian Helba Verónica Vilaplana ... Cristina Carrera Alicia Barreiro Allan Halpern S. Puig J. Malvehy 50 437 0 06 Aug 2019
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks Mingxing Tan Quoc V. Le 3DV MedIm 121 17,950 0 28 May 2019
Unmasking Clever Hans Predictors and Assessing What Machines Really Learn Sebastian Lapuschkin S. Wäldchen Alexander Binder G. Montavon Wojciech Samek K. Müller 71 1,005 0 26 Feb 2019
Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations A. Ross M. C. Hughes Finale Doshi-Velez FAtt 108 585 0 10 Mar 2017
Visualizing and Understanding Convolutional Networks Matthew D. Zeiler Rob Fergus FAtt SSL 329 15,825 0 12 Nov 2013