Pink: Unveiling the Power of Referential Comprehension for Multi-modal LLMs

A benchmark and analysis for fine-grained visual comprehension (FGVC) tasks in large vision language models (LVLMs).

[ICLR 2024 Oral] Less is More: Fewer Interpretable Region via Submodular Subset Selection

Generate adversarial patches against YOLOv5 🚀

YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-Time Object Detection

一些关于目标检测的脚本的改进思路代码，详细请看readme.md