Official implementation of SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference

[ECCV 2024] The official code of paper "Open-Vocabulary SAM".

Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

Official implementation of "Why are Visually-Grounded Language Models Bad at Image Classification?" (NeurIPS 2024)

Image Classification Testing with LLMs

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

GPT4Vis: What Can GPT-4 Do for Zero-shot Visual Recognition?

Code for Label Propagation for Zero-shot Classification with Vision-Language Models (CVPR2024)

A curated list of resources for Partial-Multi-Label-Learning

Exploring Structured Semantic Prior for Multi Label Recognition with Incomplete Labels [CVPR 2023]

[ICCV 2023] StreamPETR: Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection

Multi-label Image Recognition with Partial Labels (IJCV'24, ESWA'24, AAAI'22)

[2024 ACM MM] Official PyTorch implementation of the paper "Text-Region Matching for Multi-Label Image Recognition with Missing Labels"

This repo officially implements (IJCAI2024) TAI++: Text as Image for Multi-Label Image Classification by Co-Learning Transferable Prompt.

Code for Deep Quaternion Networks

Implementation of SSPA

Unofficial Implementation to CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image Classification [ICCV'23]

[ICLR 2024] Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models.

Collection of awesome test-time (domain/batch/instance) adaptation methods

CatVTON is a simple and efficient virtual try-on diffusion model with 1) Lightweight Network (899.06M parameters totally), 2) Parameter-Efficient Training (49.57M parameters trainable) and 3) Simpl…

Model calibration in CLIP Adapters

[ICML 2024] Official implementation for "Image Fusion via Vision-Language Model".

Holds code for our CVPR'23 tutorial: All Things ViTs: Understanding and Interpreting Attention in Vision.

The official implementation of RAR

[CVPR 2023] Official repository of paper titled "Fine-tuned CLIP models are efficient video learners".

[CVPR 2023] Effcient Frequence Domain-based Transformer for High-Quality Image Deblurring