|国家预印本平台
首页|I$^2$R: Inter and Intra-image Refinement in Few Shot Segmentation

I$^2$R: Inter and Intra-image Refinement in Few Shot Segmentation

I$^2$R: Inter and Intra-image Refinement in Few Shot Segmentation

来源:Arxiv_logoArxiv
英文摘要

The annotation bottleneck in semantic segmentation has driven significant interest in few-shot segmentation, which aims to develop segmentation models capable of generalizing rapidly to novel classes using minimal exemplars. Conventional training paradigms typically generate query prior maps by extracting masked-area features from support images, followed by making predictions guided by these prior maps. However, current approaches remain constrained by two critical limitations stemming from inter- and intra-image discrepancies, both of which significantly degrade segmentation performance: 1) The semantic gap between support and query images results in mismatched features and inaccurate prior maps; 2) Visually similar yet semantically distinct regions within support or query images lead to false negative or false positive predictions. We propose a novel FSS method called \textbf{I$^2$R}: 1) Using category-specific high level representations which aggregate global semantic cues from support and query images, enabling more precise inter-image region localization and address the first limitation. 2) Directional masking strategy that suppresses inconsistent support-query pixel pairs, which exhibit high feature similarity but conflicting mask, to mitigate the second issue. Experiments demonstrate that our method outperforms state-of-the-art approaches, achieving improvements of 1.9\% and 2.1\% in mIoU under the 1-shot setting on PASCAL-5$^i$ and COCO-20$^i$ benchmarks, respectively.

Ourui Fu、Hangzhou He、Xinliang Zhang、Lei Zhu、Shuang Zeng、ZhaoHeng Xie、Yanye Lu

计算技术、计算机技术

Ourui Fu,Hangzhou He,Xinliang Zhang,Lei Zhu,Shuang Zeng,ZhaoHeng Xie,Yanye Lu.I$^2$R: Inter and Intra-image Refinement in Few Shot Segmentation[EB/OL].(2025-07-08)[2025-07-23].https://arxiv.org/abs/2507.05838.点此复制

评论