Few-Shot Video Object Segmentation in X-Ray Angiography Using Local Matching and Spatio-Temporal Consistency Loss

Xi, Lin, Ma, Yingliang and Zhuang, Xiahai (2026) Few-Shot Video Object Segmentation in X-Ray Angiography Using Local Matching and Spatio-Temporal Consistency Loss.

Microsoft Word (rba11-Xi_etal_Fe-shot_video_obj) - Draft Version Available under License Unspecified licence. Download (1MB)

Abstract

We introduce a novel FSVOS model that employs a local matching strategy to restrict the search space to the most relevant neighboring pixels. Rather than relying on inefficient standard im2col-like implementations (e.g., spatial convolutions, depthwise convolutions and feature-shifting mechanisms) or hardware-specific CUDA kernels (e.g., deformable and neighborhood attention), which often suffer from limited portability across non-CUDA devices, we reorganize the local sampling process through a direction-based sampling perspective. Specifically, we implement a non-parametric sampling mechanism that enables dynamically varying sampling regions. This approach provides the flexibility to adapt to diverse spatial structures without the computational costs of parametric layers and the need for model retraining. To further enhance feature coherence across frames, we design a supervised spatio-temporal contrastive learning scheme that enforces consistency in feature representations. In addition, we introduce a publicly available benchmark dataset for multi-object segmentation in X-ray angiography videos (MOSXAV), featuring detailed, manually labeled segmentation ground truth. Extensive experiments on the CADICA, XACV, and MOSXAV datasets show that our proposed FSVOS method outperforms current state-of-the-art video segmentation methods in terms of segmentation accuracy and generalization capability (i.e., seen and unseen categories). This work offers enhanced flexibility and potential for a wide range of clinical applications.

Item Type:	Article
Uncontrolled Keywords:	x-ray video segmentation,few-shot video object segmentation,spatio-temporal consistency,medical image dataset
Faculty \ School:	Faculty of Science > School of Computing Sciences
UEA Research Groups:	Faculty of Science > Research Groups > Data Science and AI Faculty of Science > Research Groups > Norwich Epidemiology Centre Faculty of Medicine and Health Sciences > Research Groups > Norwich Epidemiology Centre Faculty of Science > Research Groups > Visual Computing and Signal Processing
Related URLs:	https://arxiv.org/pdf/2601.00988v1
Depositing User:	LivePure Connector
Date Deposited:	06 Jan 2026 13:30
Last Modified:	06 Jan 2026 13:30
URI:	https://ueaeprints.uea.ac.uk/id/eprint/101532
DOI:

Downloads

Actions (login required)

View Item