SegCompass: Exploring Interpretable Alignment with Sparse Autoencoders for Enhanced Reasoning Segmentation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lu, Zhenyu, Li, Liupeng, Wang, Jinpeng, Kang, Haoqian, Feng, Yan, Chen, Ke, Wang, Yaowei
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Machine Learning Multimedia Image and Video Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2605.22658