Few-Shot Object Detection via Spatial-Channel State Space Model
Xin, Zhimeng Wu, Tianxu Zou, Yixiong Chen, Shiming Fu, Dingjie You, Xinge
Xin, Zhimeng
Wu, Tianxu
Zou, Yixiong
Chen, Shiming
Fu, Dingjie
You, Xinge
Supervisor
Department
Computer Vision
Embargo End Date
Type
Journal article
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Due to the limited training samples in few-shot object detection (FSOD), we observe that current methods may struggle to accurately extract effective features from each channel. Specifically, this issue manifests in two aspects: i) channels with high weights may not necessarily be effective, and ii) channels with low weights may still hold significant value. To handle this problem, we consider utilizing inter-channel correlation to ensure that the novel model can effectively highlight relevant channels and rectify incorrect ones, thereby strengthening channel quality. Since the channel sequence is also 1-dimensional, its similarity with the temporal sequence inspires us to take Mamba for modeling the correlation in the channel sequence Based on this concept, we propose the Spatial-Channel State Space Modeling (SCSM) module for spatial-channel-sequence modeling to accurately extract effective features from each channel. In SCSM, we design the Spatial Feature Modeling (SFM) module to ensure the quality of spatial feature representations. We then introduce the Channel State Modeling (CSM) module, which treats channels as a 1-dimensional sequence and take mamba to capture the correlation between channels. Extensive experiments on the VOC and COCO datasets show that the SCSM module enables the novel detector to improve the quality of channel feature representations and achieve state-of-the-art performance.
Citation
Z. Xin, T. Wu, Y. Zou, S. Chen, D. Fu and X. You, "Few-Shot Object Detection via Spatial-Channel State Space Model," in IEEE Transactions on Circuits and Systems for Video Technology, doi: 10.1109/TCSVT.2025.3642750
Source
IEEE Transactions on Circuits and Systems for Video Technology
Conference
Keywords
Channel feature modeling, Few-shot object detection, State space model
Subjects
Source
Publisher
IEEE