facebookresearch / DejaVu
Repository for the paper Do SSL Models Have Déjà Vu? A Case of Unintended Memorization in Self-supervised Learning
☆37Updated last year
Related projects ⓘ
Alternatives and complementary repositories for DejaVu
- Code for T-MARS data filtering☆35Updated last year
- This is a PyTorch implementation of the paperViP A Differentially Private Foundation Model for Computer Vision☆37Updated last year
- ☆26Updated 2 years ago
- Experiments for "A Closer Look at In-Context Learning under Distribution Shifts"☆20Updated last year
- ☆17Updated 2 years ago
- [ICLR2024] (EvALign-ICL Benchmark) Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context …☆20Updated 8 months ago
- Recycling diverse models☆43Updated last year
- DiWA: Diverse Weight Averaging for Out-of-Distribution Generalization☆28Updated last year
- Official repo of Progressive Data Expansion: data, code and evaluation☆27Updated 11 months ago
- Official implementation of the paper "Provable Stochastic Optimization for Global Contrastive Learning: Small Batch Does Not Harm Perform…☆19Updated last year
- Official code for the paper: "Metadata Archaeology"☆18Updated last year
- ImageNet-12k subset of ImageNet-21k (fall11)☆20Updated last year
- ☆21Updated 7 months ago
- Self-Distillation with weighted ground-truth targets; ResNet and Kernel Ridge Regression☆17Updated 3 years ago
- Patching open-vocabulary models by interpolating weights☆90Updated last year
- ☆29Updated 2 years ago
- ☆30Updated 9 months ago
- Repository for the PopulAtion Parameter Averaging (PAPA) paper☆26Updated 6 months ago
- Official implementation for Sparse MetA-Tuning (SMAT)☆14Updated 4 months ago
- Parkar and Kim et al.'s paper on Can LLMs Select Important Instructions to Annotate?"☆12Updated 4 months ago
- Dataset Interfaces: Diagnosing Model Failures Using Controllable Counterfactual Generation☆43Updated last year
- ImageNetV2 Pytorch Dataset☆37Updated last year
- Official Code Release for "Diagnosing and Rectifying Vision Models using Language" (ICLR 2023)☆32Updated last year
- Code for paper "Can contrastive learning avoid shortcut solutions?" NeurIPS 2021.☆47Updated 2 years ago
- Code for the paper Self-Supervised Learning of Split Invariant Equivariant Representations☆26Updated last year
- Code for "Are “Hierarchical” Visual Representations Hierarchical?" in NeurIPS Workshop for Symmetry and Geometry in Neural Representation…☆19Updated last year
- The official repository for our paper "The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns …☆16Updated 11 months ago
- Official implementation of "Continual Learning by Modeling Intra-Class Variation" (MOCA). [TMLR 2023]☆16Updated last year