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).
☆17Updated 5 months ago
Related projects: ⓘ
- 🔥 🔥 [ECCV 2024] Official code for "Weighted Ensemble Models Are Strong Continual Learners"☆15Updated last month
- ☆39Updated last year
- The official PyTorch Implementation of "NOTE: Robust Continual Test-time Adaptation Against Temporal Correlation (NeurIPS '22)"☆40Updated 8 months ago
- ☆56Updated last year
- Official Implementation of CVPR 2022 paper: "Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning…☆34Updated last year
- ☆40Updated 7 months ago
- [NeurIPS21] TTT++: When Does Self-supervised Test-time Training Fail or Thrive?☆56Updated 2 years ago
- [ICLR 2024 Spotlight] "Negative Label Guided OOD Detection with Pretrained Vision-Language Models"☆19Updated 6 months ago
- This codebase is the official implementation of Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization (NeurIPS2…☆93Updated 2 years ago
- [CVPR2024 Highlight] Official implementation for Transferable Visual Prompting. The paper "Exploring the Transferability of Visual Prompt…☆26Updated 2 months ago
- Code for "BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation [ICML2024]".☆32Updated 3 months ago
- Probabilistic lifElong Test-time Adaptation with seLf-training prior (PETAL)☆13Updated last year
- Test-Time Adaptation via Conjugate Pseudo-Labels☆36Updated last year
- [CVPR 2024] Official Repository for "Efficient Test-Time Adaptation of Vision-Language Models.☆51Updated 2 months ago
- Official Implementation of LADS (Latent Augmentation using Domain descriptionS)☆49Updated last year
- Code for Continuously Changing Corruptions (CCC) benchmark + evaluation☆28Updated 3 weeks ago
- PyTorch implementation of POEM (Out-of-distribution detection with posterior sampling), ICML 2022☆28Updated last year
- [ICML23] On Pitfalls of Test-Time Adaptation☆100Updated 5 months ago
- Code for ICML 2022 paper — Efficient Test-Time Model Adaptation without Forgetting☆103Updated last year
- Code for ICML2023 paper, DDGR: Continual Learning with Deep Diffusion-based Generative Replay.☆29Updated last year
- [CVPR23] "Understanding and Improving Visual Prompting: A Label-Mapping Perspective" by Aochuan Chen, Yuguang Yao, Pin-Yu Chen, Yihua Zha…☆50Updated last year
- Towards Unified and Effective Domain Generalization☆28Updated 9 months ago
- PyTorch implementation for the paper Class-incremental Novel Class Discovery (ECCV 2022)☆65Updated last week
- Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need (IJCV 2024)☆108Updated 3 weeks ago
- The code of the paper "Minimizing the Accumulated Trajectory Error to Improve Dataset Distillation" (CVPR2023)☆38Updated last year
- Official Code for NeurIPS 2022 Paper: How Mask Matters: Towards Theoretical Understandings of Masked Autoencoders☆53Updated 10 months ago
- Test-time adaptation via Nearest neighbor information (TAST), submitted to ICLR'23☆18Updated last year
- Official Implementation of paper: PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discovery…☆39Updated last year
- Code for CVPR2022 paper "Not Just Selection, but Exploration: Online Class-Incremental Continual Learning via Dual View Consistency"☆23Updated 2 years ago
- [TMLR'24] This repository includes the official implementation our paper "Unleashing the Power of Visual Prompting At the Pixel Level"☆37Updated 4 months ago