mertyg / beyond-confidence-atypicality
Repository for the NeurIPS 2023 paper "Beyond Confidence: Reliable Models Should Also Consider Atypicality"
☆12Updated 10 months ago
Alternatives and similar repositories for beyond-confidence-atypicality:
Users that are interested in beyond-confidence-atypicality are comparing it to the libraries listed below
- ☆12Updated last year
- ☆30Updated 3 years ago
- ☆21Updated 2 years ago
- Wrap around any model to output differentially private prediction sets with finite sample validity on any dataset.☆17Updated last year
- Post-processing for fair classification☆13Updated 2 months ago
- Benchmark for Natural Temporal Distribution Shift (NeurIPS 2022)☆65Updated last year
- Code for Environment Inference for Invariant Learning (ICML 2021 Paper)☆50Updated 3 years ago
- ☆18Updated 3 years ago
- ☆44Updated 2 years ago
- Repo for the paper: "Agree to Disagree: Diversity through Disagreement for Better Transferability"☆35Updated 2 years ago
- [ICML'24] Conformal Prediction for Deep Classifier via Label Ranking☆12Updated 9 months ago
- Code and results accompanying our paper titled RLSbench: Domain Adaptation under Relaxed Label Shift☆34Updated last year
- Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Control☆66Updated 4 months ago
- LISA for ICML 2022☆47Updated last year
- This repository contains the implementation of Concept Activation Regions, a new framework to explain deep neural networks with human con…☆11Updated 2 years ago
- Predicting Out-of-Distribution Error with the Projection Norm☆17Updated 2 years ago
- This is the project for IRM methods☆12Updated 3 years ago
- ☆18Updated 3 years ago
- Invariant-feature Subspace Recovery (ISR)☆23Updated 2 years ago
- Simple data balancing baselines for worst-group-accuracy benchmarks.☆41Updated last year
- An Empirical Study of Invariant Risk Minimization☆27Updated 4 years ago
- This repository is the official implementation of Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regulari…☆21Updated 2 years ago
- ☆14Updated last year
- AAAI, 2022☆8Updated 4 months ago
- Quantile risk minimization☆24Updated 7 months ago
- Implementation of the models and datasets used in "An Information-theoretic Approach to Distribution Shifts"☆25Updated 3 years ago
- Code for the ICLR 2021 Paper "In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness"☆12Updated 3 years ago
- DiWA: Diverse Weight Averaging for Out-of-Distribution Generalization☆29Updated 2 years ago
- Code for the paper "Getting a CLUE: A Method for Explaining Uncertainty Estimates"☆35Updated 10 months ago
- [ICLR'22] Self-supervised learning optimally robust representations for domain shift.☆23Updated 3 years ago