Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/182607
Title: Hybrid mamba for few-shot segmentation
Authors: Xu, Qianxiong
Liu, Xuanyi
Zhu, Lanyun
Lin, Guosheng
Long, Cheng
Li, Ziyue
Zhao, Rui
Keywords: Computer and Information Science
Issue Date: 2024
Source: Xu, Q., Liu, X., Zhu, L., Lin, G., Long, C., Li, Z. & Zhao, R. (2024). Hybrid mamba for few-shot segmentation. 38th Conference on Neural Information Processing Systems (NeurIPS 2024).
Project: IAF-ICP 
Conference: 38th Conference on Neural Information Processing Systems (NeurIPS 2024)
Abstract: Many few-shot segmentation (FSS) methods use cross attention to fuse support foreground (FG) into query features, regardless of the quadratic complexity. A recent advance Mamba can also well capture intra-sequence dependencies, yet the complexity is only linear. Hence, we aim to devise a cross (attention-like) Mamba to capture inter-sequence dependencies for FSS. A simple idea is to scan on support features to selectively compress them into the hidden state, which is then used as the initial hidden state to sequentially scan query features. Nevertheless, it suffers from (1) support forgetting issue: query features will also gradually be compressed when scanning on them, so the support features in hidden state keep reducing, and many query pixels cannot fuse sufficient support features; (2) intra-class gap issue: query FG is essentially more similar to itself rather than to support FG, i.e., query may prefer not to fuse support features but their own ones from the hidden state, yet the success of FSS relies on the effective use of support information. To tackle them, we design a hybrid Mamba network (HMNet), including (1) a support recapped Mamba to periodically recap the support features when scanning query, so the hidden state can always contain rich support information; (2) a query intercepted Mamba to forbid the mutual interactions among query pixels, and encourage them to fuse more support features from the hidden state. Consequently, the support information is better utilized, leading to better performance. Extensive experiments have been conducted on two public benchmarks, showing the superiority of HMNet. The code is available at https://github.com/Sam1224/HMNet.
URI: https://hdl.handle.net/10356/182607
URL: http://arxiv.org/abs/2409.19613v1
Schools: College of Computing and Data Science 
Research Centres: S-Lab
Rights: © 2024 NeurIPS. All rights reserved. This article may be downloaded for personal use only. Any other use requires prior permission of the copyright holder.
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:CCDS Conference Papers

Files in This Item:
File Description SizeFormat 
2409.19613v1.pdf2.52 MBAdobe PDFView/Open

Page view(s)

24
Updated on Mar 24, 2025

Download(s)

1
Updated on Mar 24, 2025

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.