MadryLab / journey-TRAK

Related projects: ⓘ

• tml-epfl / sharpness-vs-generalization
  A modern look at the relationship between sharpness and generalization [ICML 2023]
  ☆42Updated last year
• MadryLab / pretraining-distribution-shift-robustness
  ☆12Updated 6 months ago
• sail-sg / D-TRAK
  Intriguing Properties of Data Attribution on Diffusion Models (ICLR 2024)
  ☆22Updated 7 months ago
• MadryLab / failure-directions
  Distilling Model Failures as Directions in Latent Space
  ☆45Updated last year
• JonasGeiping / dataaugs
  ☆17Updated last year
• r-three / mats
  ☆22Updated 2 months ago
• MadryLab / dataset-interfaces
  Dataset Interfaces: Diagnosing Model Failures Using Controllable Counterfactual Generation
  ☆43Updated last year
• singlasahil14 / salient_imagenet
  Code for the ICLR 2022 paper. Salient Imagenet: How to discover spurious features in deep learning?
  ☆35Updated 2 years ago
• mueller-mp / SAM-ON
  ☆31Updated 7 months ago
• yossigandelsman / second_order_lens
  Official pytorch implementation of "Interpreting the Second-Order Effects of Neurons in CLIP"
  ☆25Updated last month
• JonasGeiping / fullbatchtraining
  Training vision models with full-batch gradient descent and regularization
  ☆37Updated last year
• tml-epfl / understanding-sam
  Towards Understanding Sharpness-Aware Minimization [ICML 2022]
  ☆34Updated 2 years ago
• gortizji / linearized-networks
  Source code of "What can linearized neural networks actually say about generalization?
  ☆17Updated 2 years ago
• tding1 / Neural-Collapse
  [NeurIPS 2021] A Geometric Analysis of Neural Collapse with Unconstrained Features
  ☆50Updated 2 years ago
• MadryLab / BREEDS-Benchmarks
  ☆55Updated 4 years ago
• izmailovpavel / spurious_feature_learning
  ☆40Updated last year
• modestyachts / cifar-10.2
  Host CIFAR-10.2 Data Set
  ☆13Updated 2 years ago
• MadryLab / datamodels-data
  Data for "Datamodels: Predicting Predictions with Training Data"
  ☆87Updated last year
• Newbeeer / V-information
  Code for the ICLR 2020 Paper, "A Theory of Usable Information under Computational Constraints"
  ☆22Updated 4 years ago
• erosenfeld / disagree_discrep
  Provably (and non-vacuously) bounding test error of deep neural networks under distribution shift with unlabeled test data.
  ☆9Updated 6 months ago
• MadryLab / datamodels
  ☆21Updated last year
• ryoungj / optdom
  [ICLR'22] Self-supervised learning optimally robust representations for domain shift.
  ☆23Updated 2 years ago
• MadryLab / DebuggableDeepNetworks
  ☆37Updated 3 years ago
• ethz-spylab / realistic-adv-examples
  Code for the paper "Evading Black-box Classifiers Without Breaking Eggs" [SaTML 2024]
  ☆19Updated 5 months ago
• YanNeu / spurious_imagenet
  Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNet
  ☆29Updated last year
• PolinaKirichenko / deep_feature_reweighting
  ☆102Updated 11 months ago
• rxian / fair-classification
  Post-processing for fair classification
  ☆11Updated last month
• locuslab / acr-memorization
  ☆23Updated 4 months ago
• xu-ji / information-bottleneck
  Deep Learning & Information Bottleneck
  ☆45Updated last year
• yoonholee / DivDis
  ☆39Updated last year