MST: Adaptive Multi-Scale Tokens Guided Interactive Segmentation

Interactive segmentation has gained significant attention for its application in human-computer interaction and data annotation. To address the target scale variation issue in interactive segmentation, a novel multi-scale token adaptation algorithm is proposed. By performing top-k operations across...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-02
Main Authors: Long, Xu, Li, Shanghong, Chen, Yongquan, Luo, Jun, Lai, Shiwu
Format: Article
Language:English
Subjects:
Adaptation
Algorithms
Annotations
Machine learning
Performance enhancement
Segmentation
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Interactive segmentation has gained significant attention for its application in human-computer interaction and data annotation. To address the target scale variation issue in interactive segmentation, a novel multi-scale token adaptation algorithm is proposed. By performing top-k operations across multi-scale tokens, the computational complexity is greatly simplified while ensuring performance. To enhance the robustness of multi-scale token selection, we also propose a token learning algorithm based on contrastive loss. This algorithm can effectively improve the performance of multi-scale token adaptation. Extensive benchmarking shows that the algorithm achieves state-of-the-art (SOTA) performance, compared to current methods. An interactive demo and all reproducible codes will be released at https://github.com/hahamyt/mst.
ISSN:2331-8422