Wuyxin / DISC
Discover and Cure: Concept-aware Mitigation of Spurious Correlation (ICML 2023)
☆40Updated 7 months ago
Related projects ⓘ
Alternatives and complementary repositories for DISC
- This repository is the official implementation of Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regulari…☆21Updated last year
- Repo for the paper: "Agree to Disagree: Diversity through Disagreement for Better Transferability"☆35Updated 2 years ago
- LISA for ICML 2022☆47Updated last year
- ☆15Updated 5 months ago
- Code for the paper "A Whac-A-Mole Dilemma Shortcuts Come in Multiples Where Mitigating One Amplifies Others"☆44Updated 4 months ago
- Mitigating Spurious Correlations in Multi-modal Models during Fine-tuning (ICML 2023)☆17Updated 11 months ago
- Implementation of Concept-level Debugging of Part-Prototype Networks☆11Updated last year
- ☆26Updated 9 months ago
- SpuCo is a Python package developed to further research to address spurious correlations.☆21Updated last month
- Weighted Training for Cross-Task Learning☆15Updated last year
- This is the implementation for the NeurIPS 2022 paper: ZIN: When and How to Learn Invariance Without Environment Partition?☆22Updated last year
- Code for "Surgical Fine-Tuning Improves Adaptation to Distribution Shifts" published at ICLR 2023☆28Updated last year
- Official code of "Discover and Mitigate Unknown Biases with Debiasing Alternate Networks" (ECCV 2022)☆23Updated last year
- Official implementation for NeurIPS'23 paper "Geodesic Multi-Modal Mixup for Robust Fine-Tuning"☆28Updated last month
- Benchmark for Natural Temporal Distribution Shift (NeurIPS 2022)☆63Updated last year
- Code for ICLR'24 workshop ME-FoMo-How Well Does GPT-4V(ision) Adapt to Distribution Shifts? A Preliminary Investigation☆33Updated last month
- Official code repository for Correct-N-Contrast☆20Updated 2 years ago
- Official Implementation of Avoiding spurious correlations via logit correction☆17Updated last year
- ☆22Updated 5 months ago
- Towards understanding modern generative data augmentation techniques.☆24Updated last year
- This repository is the official implementation of Dataset Condensation with Contrastive Signals (DCC), accepted at ICML 2022.☆20Updated 2 years ago
- ☆25Updated 8 months ago
- ☆19Updated 2 years ago
- ☆27Updated last year
- ☆24Updated last year
- source code for NeurIPS'24 paper "HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection"☆19Updated last month
- ☆41Updated last year
- ☆30Updated 3 years ago
- Code for paper: “What Data Benefits My Classifier?” Enhancing Model Performance and Interpretability through Influence-Based Data Selecti…☆22Updated 6 months ago
- [NeurIPS 2023] Factorized Contrastive Learning: Going Beyond Multi-view Redundancy☆60Updated last year