MaxZanella / MTALinks
[CVPR 2024] Zero-shot method for Vision-Language Models based on a robust formulation of the MeanShift algorithm for Test-time Augmentation (MTA).
☆61Updated last year
Alternatives and similar repositories for MTA
Users that are interested in MTA are comparing it to the libraries listed below
Sorting:
- [CVPR 2025 - Highlight] Official implementation of the paper "Realistic Test-Time Adaptation of Vision-Language Models" (StatA).☆56Updated last month
- [NeurIPS 2024 - Spotlight] Transduction for Vision-Language Models (TransCLIP): code for the paper "Boosting Vision-Language Models with …☆52Updated 8 months ago
- [NeurIPS 2024] WATT: Weight Average Test-Time Adaptation of CLIP☆56Updated last year
- ☆38Updated last year
- Model calibration in CLIP Adapters☆19Updated last year
- Official repository for "Online Gaussian Test-Time Adaptation of Vision-Language Models."☆31Updated last month
- [CVPR 2024] Official Repository for "Efficient Test-Time Adaptation of Vision-Language Models"☆111Updated last year
- [NeurIPS 2023] Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalization☆110Updated last year
- The official implementation for paper: Vision-Language Models are Strong Noisy Label Detectors☆15Updated 8 months ago
- LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections (NeurIPS 2023)☆29Updated 2 years ago
- Official implementations of our LaZSL (ICCV'25)☆38Updated 5 months ago
- ☆22Updated 2 weeks ago
- [CVPR'24] Validation-free few-shot adaptation of CLIP, using a well-initialized Linear Probe (ZSLP) and class-adaptive constraints (CLAP)…☆78Updated 6 months ago
- Adaptation of vision-language models (CLIP) to downstream tasks using local and global prompts.☆50Updated 5 months ago
- Official code for ICCV 2023 paper, "Improving Zero-Shot Generalization for CLIP with Synthesized Prompts"☆103Updated last year
- PyTorch Implementation for InMaP☆11Updated 2 years ago
- ☆55Updated last year
- Code for Label Propagation for Zero-shot Classification with Vision-Language Models (CVPR2024)☆44Updated last year
- Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models (AAAI 2024)☆73Updated 10 months ago
- Code for our ICCV 2023 paper "Parametric Information Maximization for Generalized Category Discovery"☆16Updated last year
- The official implementation of CVPR 24' Paper "Learning Transferable Negative Prompts for Out-of-Distribution Detection"☆59Updated last year
- Exploring prompt tuning with pseudolabels for multiple modalities, learning settings, and training strategies.☆50Updated last year
- Pytorch implementation of "Test-time Adaption against Multi-modal Reliability Bias".☆44Updated last year
- 【ICCV 2023】Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning & 【IJCV 2025】Diffusion-Enhanced Test-time Adap…☆68Updated 11 months ago
- Repo of NeurIPS23☆18Updated 2 years ago
- [NeurIPS 2024] Code for Dual Prototype Evolving for Test-Time Generalization of Vision-Language Models☆45Updated 9 months ago
- 🔥MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition [Official, ICCV 2023]☆30Updated last year
- Code of ICLR 2025 paper "DynaPrompt: Dynamic Test-Time Prompt Tuning"☆20Updated 11 months ago
- [CVPR 2024] Leveraging Vision-Language Models for Improving Domain Generalization in Image Classification☆38Updated last year
- An easy way to apply LoRA to CLIP. Implementation of the paper "Low-Rank Few-Shot Adaptation of Vision-Language Models" (CLIP-LoRA) [CVPR…☆273Updated 6 months ago