facebookresearch / DejaVu
Repository for the paper Do SSL Models Have Déjà Vu? A Case of Unintended Memorization in Self-supervised Learning
☆36Updated last year
Alternatives and similar repositories for DejaVu:
Users that are interested in DejaVu are comparing it to the libraries listed below
- This is a PyTorch implementation of the paperViP A Differentially Private Foundation Model for Computer Vision☆36Updated last year
- ☆26Updated 3 years ago
- Code for T-MARS data filtering☆35Updated last year
- [ICLR2024] (EvALign-ICL Benchmark) Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context …☆21Updated last year
- Experiments for "A Closer Look at In-Context Learning under Distribution Shifts"☆20Updated last year
- Official code for the paper: "Metadata Archaeology"☆19Updated last year
- ☆34Updated 2 years ago
- DiWA: Diverse Weight Averaging for Out-of-Distribution Generalization☆29Updated 2 years ago
- Official implementation of the paper "Provable Stochastic Optimization for Global Contrastive Learning: Small Batch Does Not Harm Perform…☆20Updated last year
- Patching open-vocabulary models by interpolating weights☆91Updated last year
- Recycling diverse models☆44Updated 2 years ago
- Self-Distillation with weighted ground-truth targets; ResNet and Kernel Ridge Regression☆17Updated 3 years ago
- ☆31Updated last year
- ☆17Updated 2 years ago
- Un-*** 50 billions multimodality dataset☆24Updated 2 years ago
- ☆29Updated 2 years ago
- A pytorch implementation of the ICCV2021 workshop paper SimDis: Simple Distillation Baselines for Improving Small Self-supervised Models☆14Updated 3 years ago
- ☆25Updated 4 years ago
- ImageNet-12k subset of ImageNet-21k (fall11)☆21Updated last year
- ☆32Updated 3 years ago
- Code for the paper Self-Supervised Learning of Split Invariant Equivariant Representations☆28Updated last year
- ☆18Updated 2 years ago
- Repository for the PopulAtion Parameter Averaging (PAPA) paper☆26Updated 11 months ago
- ☆24Updated last year
- Dataset Interfaces: Diagnosing Model Failures Using Controllable Counterfactual Generation☆45Updated 2 years ago
- Official code and data for NeurIPS 2023 paper "ImageNet-Hard: The Hardest Images Remaining from a Study of the Power of Zoom and Spatial …☆37Updated last year
- ☆22Updated 11 months ago
- Code for the CVPR 2021 paper: Understanding Failures of Deep Networks via Robust Feature Extraction☆35Updated 2 years ago
- Codebase used in the paper "Foundational Models for Continual Learning: An Empirical Study of Latent Replay".☆30Updated 2 years ago
- code for paper "Accessing higher dimensions for unsupervised word translation"☆21Updated last year