For the paper "Causal-driven Decoupled Frequency Intervention and Reassembly Constraint for Unsupervised Domain Adaptation in Medical Image Segmentation"

HuiYanEarth-SAR: A Foundation Model for High-Fidelity and Low-Cost Global Remote Sensing Imagery Generation (2026)

Official PyTorch Implementation of MM-OVSeg: Optical–SAR Fusion for Open-Vocabulary Segmentation in Remote Sensing [CVPR 2026].

[CVPR26-Highlight] Open-Vocabulary Domain Generalization in Urban-Scene Segmentation

Official Implantation of Relative Depth Guided Cross Domain Semantic Segmentation for High Resolution Satellite Remote Sensing Images

Elevate your AI research writing, no more tedious polishing ✨

[AAAI2026 Oral🌟] Towards Open Vocabulary Semantic Segmentation In Remote Sensing.

[ICCV 2023] Official implementation of the paper "A Simple Framework for Open-Vocabulary Segmentation and Detection"

A curated publication list on open vocabulary semantic segmentation and related area (e.g. zero-shot semantic segmentation) resources..

Co-SAM Benchmark for evaluating Segment Anything Model (SAM) adaptation algorithms in a Continual Learning framework

Awesome Continual/Incremental Semantic Segmentation

[IEEE TPAMI 2025] REST: Holistic Learning for End-to-End Semantic Segmentation of Whole-Scene Remote Sensing Imagery

(AAAI-2025) ChangeDiff: A Multi-Temporal Change Detection Data Generator with Flexible Text Prompts via Diffusion Model

[ECCV 2024] OneRestore: A Universal Restoration Framework for Composite Degradation

SmartTagger is a tool that leverages the Segment Anything Model (SAM) to assist in automatically generating instance segmentation labels. /SmartTagger 是一个利用 SAM (Segment Anything Model) 辅助自动生成实例分割标…

Official pytorch implementation of CPSL: class-balanced pixel-level self-labeling for domain adaptive semantic segmentation (CVPR 2022)

Official PyTorch implementation of "DiGA: Distil to Generalize and then Adapt for Domain Adaptive Semantic Segmentation" (CVPR 2023)

Contrast, Stylize and Adapt: Unsupervised Contrastive Learning Framework for Domain Adaptive Semantic Segmentation

[CVPR' 25] Official implementation of the paper "Pseudo Visible Feature Fine-Grained Fusion for Thermal Object Detection"

Source code of ”Ada4DIR: An adaptive model-driven all-in-one image restoration network for remote sensing images”

The official pytorch implementation of the paper PromptHSI: Universal Hyperspectral Image Restoration Framework for Composite Degradation.

Repository containing all the code used to generate and process the FlyAware dataset

[ECCV'24/IJCV'26] Code repo for "Toward Open Vocabulary Aerial Object Detection with CLIP-Activated Student-Teacher Learning"

Code & Dataset repository for the paper "Towards Open-Vocabulary Remote Sensing Image Semantic Segmentation"

MMOT: The First Challenging Benchmark for Drone-based Multispectral Multi-Object Tracking[NIPS 2025]

[CVPR 2024] Open-Set Domain Adaptation for Semantic Segmentation