Intellindust-AI-Lab/FT-FSOD

Use DINOv3’s powerful, self-supervised visual features + YOLOv12’s blazing-fast detection, all in one repo. Whether you have only a few hundred labeled images or a medium-sized dataset, DINOV3-YOLOV12 helps you get better detection accuracy — without sacrificing speed. Great for niche domains, small-data projects, or quick prototyping.

This is the official implementation of the ECCV'2022 paper "Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation".

YOLO-OMNI: A cross-domain real-time object detection framework for fisheye, drone, panorama, game-to-real, and mixed-camera scenarios.

[ICLR 2026] The implementation of the paper Foundation Visual Encoders Are Secretly Few-Shot Anomaly Detectors

[🔥Accepted by ICCV2025🔥] Official code of the paper "From Easy to Hard: Progressive Active Learning Framework for Infrared Small Target Detection with Single Point Supervision"

[CVPR 2024] Official implement of <Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation>

[Accepted by NeurIPS2026] Official code of the paper "Rethinking Infrared Small Target Detection: A Foundation- Driven Efficient Paradigm"

Gather research papers, corresponding codes (if having), reading notes and any other related materials about Hot🔥🔥🔥 fields in Computer Vision based on Deep Learning.

End-to-End Object Detection with Transformers