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).
☆59Updated 10 months ago
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).☆50Updated 6 months ago
- [NeurIPS 2024 - Spotlight] Transduction for Vision-Language Models (TransCLIP): code for the paper "Boosting Vision-Language Models with …☆52Updated 6 months ago
- [NeurIPS 2024] WATT: Weight Average Test-Time Adaptation of CLIP☆55Updated last year
- ☆38Updated last year
- [CVPR 2024] Official Repository for "Efficient Test-Time Adaptation of Vision-Language Models"☆108Updated last year
- Model calibration in CLIP Adapters☆19Updated last year
- Official implementations of our LaZSL (ICCV'25)☆36Updated 3 months ago
- LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections (NeurIPS 2023)☆29Updated last year
- PyTorch Implementation for InMaP☆10Updated 2 years ago
- [NeurIPS 2023] Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalization☆107Updated last year
- [PR 2024] TFS-ViT: Token-Level Feature Stylization for Domain Generalization☆25Updated 2 years ago
- Adaptation of vision-language models (CLIP) to downstream tasks using local and global prompts.☆49Updated 3 months ago
- The official implementation for paper: Vision-Language Models are Strong Noisy Label Detectors☆16Updated 6 months ago
- [CVPR'24] Validation-free few-shot adaptation of CLIP, using a well-initialized Linear Probe (ZSLP) and class-adaptive constraints (CLAP)…☆78Updated 4 months ago
- Official code for ICCV 2023 paper, "Improving Zero-Shot Generalization for CLIP with Synthesized Prompts"☆102Updated last year
- ☆27Updated last year
- Official repository for "Online Gaussian Test-Time Adaptation of Vision-Language Models."☆30Updated 9 months ago
- 🔥MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition [Official, ICCV 2023]☆30Updated 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…☆256Updated 4 months ago
- ☆20Updated last year
- ☆50Updated last year
- Code for Label Propagation for Zero-shot Classification with Vision-Language Models (CVPR2024)☆43Updated last year
- This repository contains the code for our CVPR 2024 paper,☆13Updated last year
- The official implementation of CVPR 24' Paper "Learning Transferable Negative Prompts for Out-of-Distribution Detection"☆58Updated last year
- Official repository of paper titled "D3Former: Debiased Dual Distilled Transformer for Incremental Learning".☆25Updated 2 years ago
- Code of ICLR 2025 paper "DynaPrompt: Dynamic Test-Time Prompt Tuning"☆19Updated 9 months ago
- [AAAI'25, CVPRW 2024] Official repository of paper titled "Learning to Prompt with Text Only Supervision for Vision-Language Models".☆113Updated 10 months ago
- The official pytorch implemention of our CVPR-2024 paper "MMA: Multi-Modal Adapter for Vision-Language Models".☆83Updated 6 months ago
- [ACCV 2024] ObjectCompose: Evaluating Resilience of Vision-Based Models on Object-to-Background Compositional Changes 🚀🚀🚀☆37Updated 9 months ago
- 【ICCV 2023】Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning & 【IJCV 2025】Diffusion-Enhanced Test-time Adap…☆68Updated 9 months ago