Out-of-Distribution Generalization

Benchmarks archive 2025-07-28

No benchmark for this task in the archive.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

4 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 258 papers with code (516 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Deep Residual Learning for Image Recognition
  10 Dec 2015 484 repositories listed Syntology ran 230 of 377 samples · 147 unverified · 187 pointer-only (licence)
  Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.
• Learning Transferable Visual Models From Natural Language Supervision
  26 Feb 2021 82 repositories listed Syntology ran 16 of 20 samples · 4 unverified · 16 pointer-only (licence)
  State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories.
• mixup: Beyond Empirical Risk Minimization
  25 Oct 2017 71 repositories listed Syntology ran 30 of 47 samples · 17 unverified · 15 pointer-only (licence)
  We also find that mixup reduces the memorization of corrupt labels, increases the robustness to adversarial examples, and stabilizes the training of generative adversarial networks.
• Masked Autoencoders Are Scalable Vision Learners
  11 Nov 2021 58 repositories listed Syntology ran 71 of 137 samples · 66 unverified · 73 pointer-only (licence)
  Our MAE approach is simple: we mask random patches of the input image and reconstruct the missing pixels.
• CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
  13 May 2019 30 repositories listed Syntology ran 17 of 24 samples · 7 unverified · 5 pointer-only (licence)
  Regional dropout strategies have been proposed to enhance the performance of convolutional neural network classifiers.
• Improved Regularization of Convolutional Neural Networks with Cutout
  15 Aug 2017 28 repositories listed Syntology ran 21 of 24 samples · 3 unverified · 5 pointer-only (licence)
  Convolutional neural networks are capable of learning powerful representational spaces, which are necessary for tackling complex learning tasks.
• Designing Network Design Spaces
  30 Mar 2020 26 repositories listed Syntology ran 11 of 53 samples · 42 unverified
  In this work, we present a new network design paradigm.
• Invariant Risk Minimization
  5 Jul 2019 18 repositories listed Syntology ran 18 of 30 samples · 12 unverified · 10 pointer-only (licence)
  We introduce Invariant Risk Minimization (IRM), a learning paradigm to estimate invariant correlations across multiple training distributions.
• AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
  5 Dec 2019 15 repositories listed Syntology ran 43 of 51 samples · 8 unverified · 25 pointer-only (licence)
  We propose AugMix, a data processing technique that is simple to implement, adds limited computational overhead, and helps models withstand unforeseen corruptions.
• An Empirical Study of Training Self-Supervised Vision Transformers
  5 Apr 2021 9 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  In this work, we go back to basics and investigate the effects of several fundamental components for training self-supervised ViT.
• Big Transfer (BiT): General Visual Representation Learning
  24 Dec 2019 9 repositories listed Syntology ran 3 of 10 samples · 7 unverified
  We conduct detailed analysis of the main components that lead to high transfer performance.
• Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization
  20 Nov 2019 8 repositories listed Syntology ran 9 of 10 samples · 1 unverified · 2 pointer-only (licence)
  Distributionally robust optimization (DRO) allows us to learn models that instead minimize the worst-case training loss over a set of pre-defined groups.
• ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
  29 Nov 2018 7 repositories listed Syntology ran 0 of 6 samples · 6 unverified
  Convolutional Neural Networks (CNNs) are commonly thought to recognise objects by learning increasingly complex representations of object shapes.
• Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
  10 Mar 2022 6 repositories listed Syntology ran 5 of 17 samples · 12 unverified
  The conventional recipe for maximizing model accuracy is to (1) train multiple models with various hyperparameters and (2) pick the individual model which performs best on a held-out validation set, discarding the…
• Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics
  22 Sep 2020 6 repositories listed Syntology ran 7 of 16 samples · 9 unverified · 3 pointer-only (licence)
  Experiments across four datasets show that these model-dependent measures reveal three distinct regions in the data map, each with pronounced characteristics.
• Pareto Invariant Risk Minimization: Towards Mitigating the Optimization Dilemma in Out-of-Distribution Generalization
  15 Jun 2022 4 repositories listed Syntology ran 6 of 10 samples · 4 unverified · 1 pointer-only (licence)
  Recently, there has been a growing surge of interest in enabling machine learning systems to generalize well to Out-of-Distribution (OOD) data.
• Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations
  6 Apr 2022 4 repositories listed Syntology ran 3 of 8 samples · 5 unverified
  Neural network classifiers can largely rely on simple spurious features, such as backgrounds, to make predictions.
• Goal Misgeneralization in Deep Reinforcement Learning
  28 May 2021 4 repositories listed Syntology ran 2 of 13 samples · 11 unverified · 1 pointer-only (licence)
  We study goal misgeneralization, a type of out-of-distribution generalization failure in reinforcement learning (RL).
• Synbols: Probing Learning Algorithms with Synthetic Datasets
  14 Sep 2020 4 repositories listed
  Progress in the field of machine learning has been fueled by the introduction of benchmark datasets pushing the limits of existing algorithms.
• Out-of-Distribution Generalization via Risk Extrapolation (REx)
  2 Mar 2020 4 repositories listed Syntology ran 3 of 4 samples · 1 unverified · 3 pointer-only (licence)
  Distributional shift is one of the major obstacles when transferring machine learning prediction systems from the lab to the real world.
• LIMO: Less is More for Reasoning
  5 Feb 2025 3 repositories listed
  While conventional wisdom suggests that sophisticated reasoning tasks demand extensive training data (>100, 000 examples), we demonstrate that complex mathematical reasoning abilities can be effectively elicited with…
• Uncovering the Limits of Machine Learning for Automatic Vulnerability Detection
  28 Jun 2023 3 repositories listed
  Using six ML4VD techniques and two datasets, we find (a) that state-of-the-art models severely overfit to unrelated features for predicting the vulnerabilities in the testing data, (b) that the performance gained by…
• Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs
  11 Feb 2022 3 repositories listed Syntology ran 1 of 1 samples · 0 unverified
  Despite recent success in using the invariance principle for out-of-distribution (OOD) generalization on Euclidean data (e.
• Radon cumulative distribution transform subspace modeling for image classification
  7 Apr 2020 3 repositories listed
  We present a new supervised image classification method applicable to a broad class of image deformation models.
• Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation
  26 Nov 2019 3 repositories listed Syntology ran 0 of 12 samples · 12 unverified
  We design a simple but surprisingly effective visual recognition benchmark for studying bias mitigation.
• Beyond Message Passing: Neural Graph Pattern Machine
  30 Jan 2025 2 repositories listed Syntology ran 6 of 11 samples · 5 unverified
  Graph learning tasks often hinge on identifying key substructure patterns -- such as triadic closures in social networks or benzene rings in molecular graphs -- that underpin downstream performance.
• A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptation
  25 Oct 2024 2 repositories listed
  Consequently, there has been a surge in research on graph machine learning under distribution shifts, aiming to train models to achieve satisfactory performance on out-of-distribution (OOD) test data.
• MVMoE: Multi-Task Vehicle Routing Solver with Mixture-of-Experts
  2 May 2024 2 repositories listed Syntology ran 4 of 5 samples · 1 unverified
  Learning to solve vehicle routing problems (VRPs) has garnered much attention.
• The Causal Chambers: Real Physical Systems as a Testbed for AI Methodology
  17 Apr 2024 2 repositories listed Syntology ran 3 of 29 samples · 26 unverified
  The devices, which we call causal chambers, are computer-controlled laboratories that allow us to manipulate and measure an array of variables from these physical systems, providing a rich testbed for algorithms from a…
• xVal: A Continuous Numerical Tokenization for Scientific Language Models
  4 Oct 2023 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  Due in part to their discontinuous and discrete default encodings for numbers, Large Language Models (LLMs) have not yet been commonly used to process numerically-dense scientific datasets.

Syntology lines on 25 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.