Stars
Code for ICCV 2023 work "Generalized Few-Shot Point Cloud Segmentation Via Geometric Words"
Novel Category Discovery with X-Agent Attention for Open-Vocabulary Semantic Segmentation【ACMMM2025】
Paper list and datasets for industrial image anomaly/defect detection (updating). 工业异常/瑕疵检测论文及数据集检索库(持续更新)。
Curated collection of papers in MoE model inference
[AAAI 2025] Official implement of SAM-Aware Graph Prompt Reasoning Network for Cross-Domain Few-Shot Segmentation
Free ChatGPT&DeepSeek API Key，免费ChatGPT&DeepSeek API。免费接入DeepSeek API和GPT4 API，支持 gpt | deepseek | claude | gemini | grok 等排名靠前的常用大模型。
[ICCV 2023] Prompt-aligned Gradient for Prompt Tuning
[NeurIPS'24] Leveraging Hallucinations to Reduce Manual Prompt Dependency in Promptable Segmentation
a collection of AWESOME things about Optimal Transport in Deep Learning
Implementation of Zero-Shot Video Semantic Segmentation [CVPR 2025]
A curated list of awesome prompt/adapter learning methods for vision-language models like CLIP.
Unlocking the Power of SAM 2 for Few-Shot Segmentation (ICML 2025)
[NeurIPS2024] Repo for the paper `ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models'
Official implementations of our LaZSL (ICCV'25)
The Official PyTorch Implementation of OTSeg: Multi-prompt Sinkhorn Attention for Zero-Shot Semantic Segmentation
Official implementation of "OV-COAST: Cost Aggregation with Optimal Transport for Open-Vocabulary Semantic Segmentation" [CVPRW 2025]
[AAAI 2025] Explore In-Context Segmentation via Latent Diffusion Models
A latent text-to-image diffusion model
[CVPR 2025] DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation & [ICLR 2024] DFormer & [NeuriPS 2025] OmniSegmentor
[CVPR 2024] PixelLM is an effective and efficient LMM for pixel-level reasoning and understanding.
[CVPR2025] Project for "HyperSeg: Towards Universal Visual Segmentation with Large Language Model".
OctoLinker — Links together, what belongs together
External Knowledge Injection for CLIP-Based Class-Incremental Learning (ICCV 2025)