A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others

9 December 2022

Cristian Canton Ferrer

Chenliang Xu

Mark Ibrahim

ArXiv PDF HTML

Papers citing "A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others"

22 / 22 papers shown

Title
Are We Done with Object-Centric Learning? Alexander Rubinstein Ameya Prabhu Matthias Bethge Seong Joon Oh OCL 622 0 0 09 Apr 2025
Sebra: Debiasing Through Self-Guided Bias Ranking Adarsh Kappiyath Abhra Chaudhuri Ajay Jaiswal Ziquan Liu Yunpeng Li Xiatian Zhu L. Yin CML 103 1 1 30 Jan 2025
UnLearning from Experience to Avoid Spurious Correlations Jeff Mitchell Jesús Martínez del Rincón Niall McLaughlin 36 0 0 04 Sep 2024
Exposing Image Classifier Shortcuts with Counterfactual Frequency (CoF) Tables James Hinns David Martens 41 2 0 24 May 2024
Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation Model Huan Ma Yan Zhu Changqing Zhang Peilin Zhao Baoyuan Wu Long-Kai Huang Qinghua Hu Bing Wu VLM 67 1 0 01 Mar 2024
Labeling Neural Representations with Inverse Recognition Kirill Bykov Laura Kopf Shinichi Nakajima Marius Kloft Marina M.-C. Höhne BDL 21 15 0 22 Nov 2023
Partition-and-Debias: Agnostic Biases Mitigation via A Mixture of Biases-Specific Experts Jiaxuan Li D. Vo Hideki Nakayama 26 3 0 19 Aug 2023
Empirically Validating Conformal Prediction on Modern Vision Architectures Under Distribution Shift and Long-tailed Data Kevin Kasa Graham W. Taylor 32 2 0 03 Jul 2023
Confidence-Based Model Selection: When to Take Shortcuts for Subpopulation Shifts Annie S. Chen Yoonho Lee Amrith Rajagopal Setlur Sergey Levine Chelsea Finn OOD 16 5 0 19 Jun 2023
Echoes: Unsupervised Debiasing via Pseudo-bias Labeling in an Echo Chamber Rui Hu Yahan Tu Jitao Sang 27 2 0 06 May 2023
Overwriting Pretrained Bias with Finetuning Data Angelina Wang Olga Russakovsky 21 29 0 10 Mar 2023
Mark My Words: Dangers of Watermarked Images in ImageNet Kirill Bykov Klaus-Robert Muller Marina M.-C. Höhne 43 4 0 09 Mar 2023
Project and Probe: Sample-Efficient Domain Adaptation by Interpolating Orthogonal Features Annie S. Chen Yoonho Lee Amrith Rajagopal Setlur Sergey Levine Chelsea Finn VLM 26 9 0 10 Feb 2023
Improving Domain Generalization with Domain Relations Huaxiu Yao Xinyu Yang Xinyi Pan Shengchao Liu Pang Wei Koh Chelsea Finn OOD AI4CE 47 8 0 06 Feb 2023
Men Also Do Laundry: Multi-Attribute Bias Amplification Dora Zhao Jerone T. A. Andrews Alice Xiang FaML 28 20 0 21 Oct 2022
Masked Autoencoders Are Scalable Vision Learners Kaiming He Xinlei Chen Saining Xie Yanghao Li Piotr Dollár Ross B. Girshick ViT TPM 305 7,434 0 11 Nov 2021
Which Shortcut Cues Will DNNs Choose? A Study from the Parameter-Space Perspective Luca Scimeca Seong Joon Oh Sanghyuk Chun Michael Poli Sangdoo Yun OOD 376 49 0 06 Oct 2021
ResNet strikes back: An improved training procedure in timm Ross Wightman Hugo Touvron Hervé Jégou AI4TS 209 487 0 01 Oct 2021
DiagViB-6: A Diagnostic Benchmark Suite for Vision Models in the Presence of Shortcut and Generalization Opportunities Elias Eulig Piyapat Saranrittichai Chaithanya Kumar Mummadi K. Rambach William H. Beluch Xiahan Shi Volker Fischer 140 11 0 12 Aug 2021
Unsupervised Learning of Debiased Representations with Pseudo-Attributes Seonguk Seo Joon-Young Lee Bohyung Han FaML 68 48 0 06 Aug 2021
If your data distribution shifts, use self-learning E. Rusak Steffen Schneider George Pachitariu L. Eck Peter V. Gehler Oliver Bringmann Wieland Brendel Matthias Bethge VLM OOD TTA 77 29 0 27 Apr 2021
Estimating Example Difficulty Using Variance of Gradients Chirag Agarwal Daniel D'souza Sara Hooker 208 107 0 26 Aug 2020