taeckyung / SoTTA
This is the official PyTorch Implementation of "SoTTA: Robust Test-Time Adaptation on Noisy Data Streams (NeurIPS '23)" by Taesik Gong*, Yewon Kim*, Taeckyung Lee*, Sorn Chottananurak, and Sung-Ju Lee (* Equal contribution).
☆18Updated 8 months ago
Related projects ⓘ
Alternatives and complementary repositories for SoTTA
- Code for ICML 2024 paper (Oral) — Test-Time Model Adaptation with Only Forward Passes☆51Updated 3 months ago
- ☆41Updated last year
- Official Code for NeurIPS 2022 Paper: How Mask Matters: Towards Theoretical Understandings of Masked Autoencoders☆55Updated last year
- Code for Continuously Changing Corruptions (CCC) benchmark + evaluation☆29Updated 3 months ago
- [NeurIPS21] TTT++: When Does Self-supervised Test-time Training Fail or Thrive?☆59Updated 2 years ago
- Official Implementation of CVPR 2022 paper: "Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning…☆34Updated last year
- Official Repository of "On the Effectiveness of LayerNorm Tuning for Continual Learning in Vision Transformers" (Visual Continual Learnin…☆8Updated 10 months ago
- [CVPR 2024] Official Repository for "Efficient Test-Time Adaptation of Vision-Language Models"☆63Updated 4 months ago
- The official PyTorch Implementation of "NOTE: Robust Continual Test-time Adaptation Against Temporal Correlation (NeurIPS '22)"☆42Updated 11 months ago
- Test-Time Adaptation via Conjugate Pseudo-Labels☆38Updated last year
- This codebase is the official implementation of Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization (NeurIPS2…☆93Updated 2 years ago
- PyTorch implementation of POEM (Out-of-distribution detection with posterior sampling), ICML 2022☆28Updated last year
- Probabilistic lifElong Test-time Adaptation with seLf-training prior (PETAL)☆13Updated last year
- ☆47Updated 9 months ago
- 🔥 🔥 [ECCV 2024 Oral ] Official code for "Weighted Ensemble Models Are Strong Continual Learners"☆19Updated 3 months ago
- This is an official PyTorch implementation of the ICML 2023 paper AdaNPC and SIGKDD paper DRM.☆81Updated 7 months ago
- Towards Unified and Effective Domain Generalization☆29Updated 11 months ago
- [ICML23] On Pitfalls of Test-Time Adaptation☆103Updated 7 months ago
- ☆60Updated last year
- ☆13Updated 6 months ago
- ☆16Updated 2 weeks ago
- Code for ICML 2022 paper — Efficient Test-Time Model Adaptation without Forgetting☆106Updated last year
- [CVPR23] "Understanding and Improving Visual Prompting: A Label-Mapping Perspective" by Aochuan Chen, Yuguang Yao, Pin-Yu Chen, Yihua Zha…☆51Updated last year
- ☆47Updated 7 months ago
- PyTorch implementation of CIDER (How to exploit hyperspherical embeddings for out-of-distribution detection), ICLR 2023☆54Updated last year
- The code of the paper "Minimizing the Accumulated Trajectory Error to Improve Dataset Distillation" (CVPR2023)☆40Updated last year
- Distribution-Aware Prompt Tuning for Vision-Language Models (ICCV 2023)☆37Updated 11 months ago
- Code for "BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation [ICML2024]".☆38Updated 5 months ago
- This is a community implementation for the paper EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularizatio…☆25Updated last year
- Official implementation of NNCSL☆22Updated 6 months ago