Stars
InstructSAM: A Training-Free Framework for Instruction-Oriented Remote Sensing Object Recognition
[CVPR 2025] Official code repository for "MaSS13K: A Matting-level Semantic Segmentation Benchmark"
[CVPR 2025] Hybrid Global-Local Representation with Augmented Spatial Guidance for Zero-Shot Referring Image Segmentation
Official Implement of the paper "Unifying Segment Anything in Microscopy with Multimodal Large Language Model"
Code & Dataset repository for the paper "Towards Open-Vocabulary Remote Sensing Image Semantic Segmentation"
vHeat: Building Vision Models upon Heat Conduction
Implementation of the AAAI-2025 paper "ConDSeg: A General Medical Image Segmentation Framework via Contrast-Driven Feature Enhancement".
[CVPR'24] UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition
Implementation for Describe Anything: Detailed Localized Image and Video Captioning
Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformers, AIR 2023.
[CAAI AIR'24] Bilateral Reference for High-Resolution Dichotomous Image Segmentation
The official code and dataset of paper: Deep Learning in Concealed Dense Prediction
Code release for "VSCode: General Visual Salient and Camouflaged Object Detection with 2D Prompt Learning"
Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024
[CVPR 2025 Oral] SegEarth-OV: Towards Training-Free Open-Vocabulary Segmentation for Remote Sensing Images
PySegMetrics (PSM): A Python-based Simple yet Efficient Evaluation Toolbox for Segmentation-like tasks
The summary of code and paper for unified model towards context-dependent (CD) concept segmentation.
(ICML 2024) Spider: A Unified Framework for Context-dependent Concept Segmentation
This code refers to a Paper accepted at MIDL 2025 'PixelCAM: Pixel Class Activation Mapping for Histology Image Classification and ROI Localization'
[CVPR2025] Exploring CLIP’s Dense Knowledge for Weakly Supervised Semantic Segmentation
Minding Fuzzy Regions: A Data-driven Alternating Learning Paradigm for Stable Lesion Segmentation
Open-Sora: Democratizing Efficient Video Production for All