Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations

6 April 2022

Papers citing "Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations"

50 / 238 papers shown

Title
ASPIRE: Language-Guided Data Augmentation for Improving Robustness Against Spurious Correlations Sreyan Ghosh Chandra Kiran Reddy Evuru Sonal Kumar Utkarsh Tyagi Sakshi Singh Sanjoy Chowdhury Dinesh Manocha OOD 30 1 0 19 Aug 2023
Distributionally Robust Optimization and Invariant Representation Learning for Addressing Subgroup Underrepresentation: Mechanisms and Limitations Nilesh Kumar Ruby Shrestha Zhiyuan Li Linwei Wang CML OOD 26 2 0 12 Aug 2023
From Fake to Real: Pretraining on Balanced Synthetic Images to Prevent Spurious Correlations in Image Recognition Maan Qraitem Kate Saenko Bryan A. Plummer 45 4 0 08 Aug 2023
When More is Less: Incorporating Additional Datasets Can Hurt Performance By Introducing Spurious Correlations Rhys Compton Lily Zhang R. Borsoi Rajesh Ranganath OOD 41 9 0 08 Aug 2023
SYNAuG: Exploiting Synthetic Data for Data Imbalance Problems Moon Ye-Bin Nam Hyeon-Woo Wonseok Choi Nayeong Kim Suha Kwak Tae-Hyun Oh DiffM 23 3 0 02 Aug 2023
Is Last Layer Re-Training Truly Sufficient for Robustness to Spurious Correlations? Phuong Quynh Le Jorg Schlotterer Christin Seifert OOD 16 6 0 01 Aug 2023
Does Progress On Object Recognition Benchmarks Improve Real-World Generalization? Megan Richards Polina Kirichenko Diane Bouchacourt Mark Ibrahim VLM 68 13 0 24 Jul 2023
Interpreting and Correcting Medical Image Classification with PIP-Net Meike Nauta J. H. Hegeman J. Geerdink Jorg Schlotterer M. V. Keulen Christin Seifert MedIm 27 11 0 19 Jul 2023
Spuriosity Didn't Kill the Classifier: Using Invariant Predictions to Harness Spurious Features Cian Eastwood Shashank Singh Andrei Liviu Nicolicioiu Marin Vlastelica Julius von Kügelgen Bernhard Schölkopf OOD 20 17 0 19 Jul 2023
Quantification of Uncertainty with Adversarial Models Kajetan Schweighofer L. Aichberger Mykyta Ielanskyi G. Klambauer Sepp Hochreiter UQCV 40 14 0 06 Jul 2023
Leveraging Task Structures for Improved Identifiability in Neural Network Representations Wenlin Chen Julien Horwood Juyeon Heo José Miguel Hernández-Lobato CML 30 1 0 26 Jun 2023
Identifying and Disentangling Spurious Features in Pretrained Image Representations R. Darbinyan Hrayr Harutyunyan Aram H. Markosyan Hrant Khachatrian 32 2 0 22 Jun 2023
Challenges and Opportunities in Improving Worst-Group Generalization in Presence of Spurious Features S. Joshi Yu Yang Yihao Xue Wenhan Yang Baharan Mirzasoleiman 30 2 0 21 Jun 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
Simple and Fast Group Robustness by Automatic Feature Reweighting Shi Qiu Andres Potapczynski Pavel Izmailov A. Wilson OOD 67 53 0 19 Jun 2023
Robust Learning with Progressive Data Expansion Against Spurious Correlation Yihe Deng Yu Yang Baharan Mirzasoleiman Quanquan Gu OOD MLT 21 24 0 08 Jun 2023
LIV: Language-Image Representations and Rewards for Robotic Control Yecheng Jason Ma William Liang Vaidehi Som Vikash Kumar Amy Zhang Osbert Bastani Dinesh Jayaraman LM&Ro 33 121 0 01 Jun 2023
(Almost) Provable Error Bounds Under Distribution Shift via Disagreement Discrepancy Elan Rosenfeld Saurabh Garg UQCV 34 4 0 01 Jun 2023
What Can We Learn from Unlearnable Datasets? Pedro Sandoval-Segura Vasu Singla Jonas Geiping Micah Goldblum Tom Goldstein 21 14 0 30 May 2023
Identifying Spurious Biases Early in Training through the Lens of Simplicity Bias Yu Yang Eric Gan Gintare Karolina Dziugaite Baharan Mirzasoleiman 26 25 0 30 May 2023
Few-shot Adaptation to Distribution Shifts By Mixing Source and Target Embeddings Yihao Xue Ali Payani Yu Yang Baharan Mirzasoleiman VLM 26 4 0 23 May 2023
Understanding and Mitigating Spurious Correlations in Text Classification with Neighborhood Analysis Oscar Chew Hsuan-Tien Lin Kai-Wei Chang Kuan-Hao Huang 34 5 0 23 May 2023
AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptation Yi-Fan Zhang Xue Wang Kexin Jin Kun Yuan Zhang Zhang Liang Wang Rong Jin Tien-Ping Tan TTA OOD 17 42 0 25 Apr 2023
Leveraging sparse and shared feature activations for disentangled representation learning Marco Fumero F. Wenzel L. Zancato Alessandro Achille Emanuele Rodolà Stefano Soatto Bernhard Schölkopf Francesco Locatello OOD DRL 39 22 0 17 Apr 2023
Preemptively Pruning Clever-Hans Strategies in Deep Neural Networks Lorenz Linhardt Klaus-Robert Muller G. Montavon AAML 26 7 0 12 Apr 2023
Last-Layer Fairness Fine-tuning is Simple and Effective for Neural Networks Yuzhen Mao Zhun Deng Huaxiu Yao Ting Ye Kenji Kawaguchi James Zou 38 20 0 08 Apr 2023
Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence? Arjun Majumdar Karmesh Yadav Sergio Arnaud Yecheng Jason Ma Claire Chen ... Dhruv Batra Yixin Lin Oleksandr Maksymets Aravind Rajeswaran Franziska Meier LM&Ro 21 173 0 31 Mar 2023
A Closer Look at Model Adaptation using Feature Distortion and Simplicity Bias Puja Trivedi Danai Koutra Jayaraman J. Thiagarajan AAML 40 17 0 23 Mar 2023
Continual Learning in the Presence of Spurious Correlation Donggyu Lee Sangwon Jung Taesup Moon CLL 22 2 0 21 Mar 2023
Domain Generalization via Nuclear Norm Regularization Zhenmei Shi Yifei Ming Ying Fan Frederic Sala Yingyu Liang 30 12 0 13 Mar 2023
Use Perturbations when Learning from Explanations Juyeon Heo Vihari Piratla Matthew Wicker Adrian Weller AAML 38 1 0 11 Mar 2023
Overwriting Pretrained Bias with Finetuning Data Angelina Wang Olga Russakovsky 26 29 0 10 Mar 2023
Training, Architecture, and Prior for Deterministic Uncertainty Methods Bertrand Charpentier Chenxiang Zhang Stephan Günnemann UQCV OOD AI4CE 34 6 0 10 Mar 2023
Spawrious: A Benchmark for Fine Control of Spurious Correlation Biases Aengus Lynch G. Dovonon Jean Kaddour Ricardo M. A. Silva 189 30 0 09 Mar 2023
Debiased Distillation by Transplanting the Last Layer Jiwoon Lee Jaeho Lee 23 3 0 22 Feb 2023
Beyond Distribution Shift: Spurious Features Through the Lens of Training Dynamics Nihal Murali A. Puli Ke Yu Rajesh Ranganath Kayhan Batmanghelich AAML 43 8 0 18 Feb 2023
Pushing the Accuracy-Group Robustness Frontier with Introspective Self-play J. Liu Krishnamurthy Dvijotham Jihyeon Janel Lee Quan Yuan Martin Strobel Balaji Lakshminarayanan Deepak Ramachandran 23 5 0 11 Feb 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 32 9 0 10 Feb 2023
Shortcut Detection with Variational Autoencoders Nicolas M. Muller Simon Roschmann Shahbaz Khan Philip Sperl Konstantin Böttinger AAML DRL 34 1 0 08 Feb 2023
Bitrate-Constrained DRO: Beyond Worst Case Robustness To Unknown Group Shifts Amrith Rajagopal Setlur D. Dennis Benjamin Eysenbach Aditi Raghunathan Chelsea Finn Virginia Smith Sergey Levine OOD 35 11 0 06 Feb 2023
Hyper-parameter Tuning for Fair Classification without Sensitive Attribute Access A. Veldanda Ivan Brugere Sanghamitra Dutta Alan Mishler S. Garg 36 5 0 02 Feb 2023
Debiasing Vision-Language Models via Biased Prompts Ching-Yao Chuang Varun Jampani Yuanzhen Li Antonio Torralba Stefanie Jegelka VLM 30 96 0 31 Jan 2023
Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces Pattarawat Chormai J. Herrmann Klaus-Robert Muller G. Montavon FAtt 48 17 0 30 Dec 2022
Learning useful representations for shifting tasks and distributions Jianyu Zhang Léon Bottou OOD 34 13 0 14 Dec 2022
Simplicity Bias Leads to Amplified Performance Disparities Samuel J. Bell Levent Sagun 24 12 0 13 Dec 2022
You Only Need a Good Embeddings Extractor to Fix Spurious Correlations Raghav Mehta Vítor Albiero Li Chen Ivan Evtimov Tamar Glaser Zhiheng Li Tal Hassner 26 17 0 12 Dec 2022
A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others Zhiheng Li Ivan Evtimov Albert Gordo C. Hazirbas Tal Hassner Cristian Canton Ferrer Chenliang Xu Mark Ibrahim 34 71 0 09 Dec 2022
Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases Mazda Moayeri Wenxiao Wang Sahil Singla S. Feizi 69 14 0 05 Dec 2022
Avoiding spurious correlations via logit correction Sheng Liu Xu Zhang Nitesh Sekhar Yue Wu Prateek Singhal C. Fernandez‐Granda 25 29 0 02 Dec 2022
AGRO: Adversarial Discovery of Error-prone groups for Robust Optimization Bhargavi Paranjape Pradeep Dasigi Vivek Srikumar Luke Zettlemoyer Hannaneh Hajishirzi 36 7 0 02 Dec 2022