Segment-Any-Anomaly

https://arxiv.org/pdf/2306.09067.pdf

Winning Solution for the CVPR2023 Visual Anomaly and Novelty Detection Challenge: Multimodal Prompting for Data-centric Anomaly Detection

https://github.com/caoyunkang/Segment-Any-Anomaly

The Second-place Solution for CVPR VISION 23 Challenge Track 1 -- Data Effificient Defect Detection

https://arxiv.org/abs/2306.14116

https://github.com/love6tao/Aoi-overfitting-team 可以看出是使用了 mmdet

网站

https://arxiv.org/list/cs.CV/recent

LLM 总结，论文名：A Survey on Multimodal Large Language Models https://github.com/BradyFU/Awesome-Multimodal-Large-Language-Models

加速数据瓶颈 https://github.com/libffcv/ffcv

Large Multimodal Models:Notes on CVPR 2023 Tutorial

https://arxiv.org/pdf/2306.14895.pdf

Transformer-Based Visual Segmentation: A Survey

https://arxiv.org/abs/2304.09854v2 第二版有更新 https://github.com/lxtGH/Awesome-Segmentation-With-Transformer

A Survey of Large Language Models

https://github.com/RUCAIBox/LLMSurvey

MMF

A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)
https://github.com/facebookresearch/mmf