Fetching the paper…
Reading the bibliography…
Several studies have compared the in-distribution (ID) and out-of-distribution (OOD) performance of models in computer vision and NLP.
Improving predictive inference under covariate shift by weighting the log-likelihood function
Hidetoshi Shimodaira · 2000
Earlier work this paper cites.
Learning what makes a difference from counterfactual examples and gradient supervision
Damien Teney, Ehsan Abbasnedjad, and Anton van den Hengel · 2004
Earlier work this paper cites.
Learning to extract motion from videos in convolutional neural networks
Damien Teney and Martial Hebert · 2016
Earlier work this paper cites.
Deeper, broader and artier domain generalization
Da Li, Yongxin Yang, Yi-Zhe Song, and Timothy M Hospedales · 2017
Earlier work this paper cites.
mixup: Beyond empirical risk minimization
Hongyi Zhang, Moustapha Cisse, Yann N Dauphin, and David Lopez-Paz · 2017
Earlier work this paper cites.
Detecting and correcting for label shift with black box predictors
Zachary Lipton, Yu-Xiang Wang, and Alexander Smola · 2018
Earlier work this paper cites.
Learning qualitatively diverse and interpretable rules for classification
Andrew Slavin Ross, Weiwei Pan, and Finale Doshi-Velez · 2018
Earlier work this paper cites.
Martin Arjovsky, Léon Bottou, Ishaan Gulrajani, and David Lopez-Paz · 2019
Earlier work this paper cites.
R Thomas McCoy, Junghyun Min, and Tal Linzen · 2019
Earlier work this paper cites.
Do imagenet classifiers generalize to imagenet?
Benjamin Recht, Rebecca Roelofs, Ludwig Schmidt, and Vaishaal Shankar · 2019
Earlier work this paper cites.
Shiori Sagawa, Pang Wei Koh, Tatsunori B Hashimoto, and Percy Liang · 2019
Earlier work this paper cites.
Theoretically principled trade-off between robustness and accuracy
Hongyang Zhang, Yaodong Yu, Jiantao Jiao, Eric Xing, Laurent El Ghaoui, and Michael Jordan · 2019
Earlier work this paper cites.
Counterfactual vision and language learning
Ehsan Abbasnejad, Damien Teney, Amin Parvaneh, Javen Shi, and Anton van den Hengel · 2020
Earlier work this paper cites.
Underspecification presents challenges for credibility in modern machine learning
Alexander D’Amour, Katherine Heller, Dan Moldovan, Ben Adlam, Babak Alipanahi, Alex Beutel, Christina Chen, Jonathan Deaton, Jacob Eisenstein, Matthew D Hoffman, et al · 2020
Earlier work this paper cites.
Why do classifier accuracies show linear trends under distribution shift?
Horia Mania and Suvrit Sra · 2020
Earlier work this paper cites.
The effect of natural distribution shift on question answering models
John Miller, Karl Krauth, Benjamin Recht, and Ludwig Schmidt · 2020
Earlier work this paper cites.
Understanding and mitigating the tradeoff between robustness and accuracy
Aditi Raghunathan, Sang Michael Xie, Fanny Yang, John Duchi, and Percy Liang · 2020
Earlier work this paper cites.
The risks of invariant risk minimization
Elan Rosenfeld, Pradeep Ravikumar, and Andrej Risteski · 2020
Earlier work this paper cites.
Ensembles of locally independent prediction models
Andrew Ross, Weiwei Pan, Leo Celi, and Finale Doshi-Velez · 2020
Cited alongside, same era.
BREEDS: Benchmarks for subpopulation shift
Shibani Santurkar, Dimitris Tsipras, and Aleksander Madry · 2020
Cited alongside, same era.
The pitfalls of simplicity bias in neural networks
Harshay Shah, Kaustav Tamuly, Aditi Raghunathan, Prateek Jain, and Praneeth Netrapalli · 2020
Cited alongside, same era.
Measuring robustness to natural distribution shifts in image classification
Rohan Taori, Achal Dave, Vaishaal Shankar, Nicholas Carlini, Benjamin Recht, and Ludwig Schmidt · 2020
Cited alongside, same era.
Sang Michael Xie, Ananya Kumar, Robbie Jones, Fereshte Khani, Tengyu Ma, and Percy Liang · 2020
Representational multiplicity should be exposed, not eliminated
Ari Heljakka, Martin Trapp, Juho Kannala, and Arno Solin · 2022
Closest in time.
Simple data balancing achieves competitive worst-group-accuracy
Badr Youbi Idrissi, Martin Arjovsky, Mohammad Pezeshki, and David Lopez-Paz · 2022
Closest in time.
Linear connectivity reveals generalization strategies
Jeevesh Juneja, Rachit Bansal, Kyunghyun Cho, João Sedoc, and Naomi Saphra · 2022
Closest in time.
Deconstructing distributions: A pointwise framework of learning
Gal Kaplun, Nikhil Ghosh, Saurabh Garg, Boaz Barak, and Preetum Nakkiran · 2022
Closest in time.
Diversify and disambiguate: Learning from underspecified data
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Cited alongside, same era.
A closer look at accuracy vs. robustness
Yao-Yuan Yang, Cyrus Rashtchian, Hongyang Zhang, Russ R Salakhutdinov, and Kamalika Chaudhuri · 2020
Cited alongside, same era.
The evolution of out-of-distribution robustness throughout fine-tuning
Anders Andreassen, Yasaman Bahri, Behnam Neyshabur, and Rebecca Roelofs · 2021
Cited alongside, same era.
On robustness and transferability of convolutional neural networks
Josip Djolonga, Jessica Yung, Michael Tschannen, Rob Romijnders, Lucas Beyer, Alexander Kolesnikov, Joan Puigcerver, Matthias Minderer, Alexander D’Amour, Dan Moldovan, et al · 2021
Cited alongside, same era.
In search of lost domain generalization
Ishaan Gulrajani and David Lopez-Paz · 2021
Cited alongside, same era.
WILDS: A benchmark of in-the-wild distribution shifts
Pang Wei Koh, Shiori Sagawa, Henrik Marklund, Sang Michael Xie, Marvin Zhang, Akshay Balsubramani, Weihua Hu, Michihiro Yasunaga, Richard Lanas Phillips, Irena Gao, et al · 2021
Cited alongside, same era.
Accuracy on the line: on the strong correlation between out-of-distribution and in-distribution generalization
John P Miller, Rohan Taori, Aditi Raghunathan, Shiori Sagawa, Pang Wei Koh, Vaishaal Shankar, Percy Liang, Yair Carmon, and Ludwig Schmidt · 2021
Cited alongside, same era.
A neural anisotropic view of underspecification in deep learning
Guillermo Ortiz-Jimenez, Itamar Franco Salazar-Reque, Apostolos Modas, Seyed-Mohsen Moosavi-Dezfooli, and Pascal Frossard · 2021
Cited alongside, same era.
Yoonho Lee, Huaxiu Yao, and Chelsea Finn · 2022
Closest in time.
On the nonlinear correlation of ml performance across data subpopulations
Weixin Liang, Yining Mao, Yongchan Kwon, Xinyu Yang, and James Zou · 2022
Closest in time.
Empirical study on optimizer selection for out-of-distribution generalization
Hiroki Naganuma, Kartik Ahuja, Ioannis Mitliagkas, Shiro Takagi, Tetsuya Motokawa, Rio Yokota, Kohta Ishikawa, and Ikuro Sato · 2022
Closest in time.
Agree to disagree: Diversity through disagreement for better transferability
Matteo Pagliardini, Martin Jaggi, François Fleuret, and Sai Praneeth Karimireddy · 2022
Closest in time.
An impartial take to the CNN vs transformer robustness contest
Francesco Pinto, Philip HS Torr, and Puneet K Dokania · 2022
Closest in time.
Recycling diverse models for out-of-distribution generalization
Alexandre Ramé, Kartik Ahuja, Jianyu Zhang, Matthieu Cord, Léon Bottou, and David Lopez-Paz · 2022
Closest in time.
Which shortcut cues will dnns choose? a study from the parameter-space perspective
Luca Scimeca, Seong Joon Oh, Sanghyuk Chun, Michael Poli, and Sangdoo Yun · 2022
Closest in time.
A unified causal view of domain invariant representation learning
Zihao Wang and Victor Veitch · 2022
Closest in time.
Assaying out-of-distribution generalization in transfer learning
Florian Wenzel, Andrea Dittadi, Peter Vincent Gehler, Carl-Johann Simon-Gabriel, Max Horn, Dominik Zietlow, David Kernert, Chris Russell, Thomas Brox, Bernt Schiele, et al · 2022
Closest in time.
Feature space particle inference for neural network ensembles
Shingo Yashima, Teppei Suzuki, Kohta Ishikawa, Ikuro Sato, and Rei Kawakami · 2022
Closest in time.
Ood-bench: Quantifying and understanding two dimensions of out-of-distribution generalization
Nanyang Ye, Kaican Li, Haoyue Bai, Runpeng Yu, Lanqing Hong, Fengwei Zhou, Zhenguo Li, and Jun Zhu · 2022
Closest in time.
Sparse invariant risk minimization
Xiao Zhou, Yong Lin, Weizhong Zhang, and Tong Zhang · 2022
Closest in time.
Spawrious: A benchmark for fine control of spurious correlation biases
Aengus Lynch, Gbètondji JS Dovonon, Jean Kaddour, and Ricardo Silva · 2023
Closest in time.