BatsResearch / csp
Learning to compose soft prompts for compositional zero-shot learning.
☆87Updated last year
Alternatives and similar repositories for csp:
Users that are interested in csp are comparing it to the libraries listed below
- This repo is the official implementation of UPL (Unsupervised Prompt Learning for Vision-Language Models).☆110Updated 2 years ago
- Code and results accompanying our paper titled CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets☆55Updated last year
- Official repository for the ICCV 2023 paper: "Waffling around for Performance: Visual Classification with Random Words and Broad Concepts…☆56Updated last year
- This repository contains the code and datasets for our ICCV-W paper 'Enhancing CLIP with GPT-4: Harnessing Visual Descriptions as Prompts…☆28Updated 11 months ago
- PyTorch CZSL framework containing GQA, the open-world setting, and the CGE and CompCos methods.☆113Updated last year
- [ICLR2023] PLOT: Prompt Learning with Optimal Transport for Vision-Language Models☆153Updated last year
- Exploring prompt tuning with pseudolabels for multiple modalities, learning settings, and training strategies.☆47Updated 3 months ago
- Toolkit for Elevater Benchmark☆70Updated last year
- Repository for the paper: Teaching Structured Vision & Language Concepts to Vision & Language Models☆46Updated last year
- [ICCV 2023] Prompt-aligned Gradient for Prompt Tuning☆156Updated last year
- ☆58Updated last year
- [CVPR23 Highlight] CREPE: Can Vision-Language Foundation Models Reason Compositionally?☆32Updated last year
- ☆51Updated last year
- Test-time Prompt Tuning (TPT) for zero-shot generalization in vision-language models (NeurIPS 2022))☆162Updated 2 years ago
- 📍 Official pytorch implementation of paper "ProtoCLIP: Prototypical Contrastive Language Image Pretraining" (IEEE TNNLS)☆52Updated last year
- Code for Label Propagation for Zero-shot Classification with Vision-Language Models (CVPR2024)☆36Updated 6 months ago
- [NeurIPS 2023] Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalization☆103Updated last year
- NegCLIP.☆30Updated 2 years ago
- ☆26Updated last year
- Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models☆86Updated 11 months ago
- ☆62Updated last year
- ☆29Updated last year
- code for "Multitask Vision-Language Prompt Tuning" https://arxiv.org/abs/2211.11720☆55Updated 8 months ago
- Compress conventional Vision-Language Pre-training data☆49Updated last year
- ☆179Updated last year
- [CVPR 2023] Learning Attention as Disentangler for Compositional Zero-shot Learning☆40Updated last year
- Code for the paper: "SuS-X: Training-Free Name-Only Transfer of Vision-Language Models" [ICCV'23]☆97Updated last year
- ☆59Updated 2 years ago
- COLA: Evaluate how well your vision-language model can Compose Objects Localized with Attributes!☆24Updated 2 months ago
- Pytorch implementation of DAPrompt: https://arxiv.org/abs/2202.06687☆89Updated 2 years ago