Segment Concealed Objects with Incomplete Supervision

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: He, Chunming, Li, Kai, Zhang, Yachao, Yang, Ziyun, Pang, Youwei, Tang, Longxiang, Fang, Chengyu, Zhang, Yulun, Kong, Linghe, Li, Xiu, Farsiu, Sina
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916793795215360
author He, Chunming
Li, Kai
Zhang, Yachao
Yang, Ziyun
Pang, Youwei
Tang, Longxiang
Fang, Chengyu
Zhang, Yulun
Kong, Linghe
Li, Xiu
Farsiu, Sina
author_facet He, Chunming
Li, Kai
Zhang, Yachao
Yang, Ziyun
Pang, Youwei
Tang, Longxiang
Fang, Chengyu
Zhang, Yulun
Kong, Linghe
Li, Xiu
Farsiu, Sina
contents Incompletely-Supervised Concealed Object Segmentation (ISCOS) involves segmenting objects that seamlessly blend into their surrounding environments, utilizing incompletely annotated data, such as weak and semi-annotations, for model training. This task remains highly challenging due to (1) the limited supervision provided by the incompletely annotated training data, and (2) the difficulty of distinguishing concealed objects from the background, which arises from the intrinsic similarities in concealed scenarios. In this paper, we introduce the first unified method for ISCOS to address these challenges. To tackle the issue of incomplete supervision, we propose a unified mean-teacher framework, SEE, that leverages the vision foundation model, ``\emph{Segment Anything Model (SAM)}'', to generate pseudo-labels using coarse masks produced by the teacher model as prompts. To mitigate the effect of low-quality segmentation masks, we introduce a series of strategies for pseudo-label generation, storage, and supervision. These strategies aim to produce informative pseudo-labels, store the best pseudo-labels generated, and select the most reliable components to guide the student model, thereby ensuring robust network training. Additionally, to tackle the issue of intrinsic similarity, we design a hybrid-granularity feature grouping module that groups features at different granularities and aggregates these results. By clustering similar features, this module promotes segmentation coherence, facilitating more complete segmentation for both single-object and multiple-object images. We validate the effectiveness of our approach across multiple ISCOS tasks, and experimental results demonstrate that our method achieves state-of-the-art performance. Furthermore, SEE can serve as a plug-and-play solution, enhancing the performance of existing models.
format Preprint
id arxiv_https___arxiv_org_abs_2506_08955
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Segment Concealed Objects with Incomplete Supervision
He, Chunming
Li, Kai
Zhang, Yachao
Yang, Ziyun
Pang, Youwei
Tang, Longxiang
Fang, Chengyu
Zhang, Yulun
Kong, Linghe
Li, Xiu
Farsiu, Sina
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Incompletely-Supervised Concealed Object Segmentation (ISCOS) involves segmenting objects that seamlessly blend into their surrounding environments, utilizing incompletely annotated data, such as weak and semi-annotations, for model training. This task remains highly challenging due to (1) the limited supervision provided by the incompletely annotated training data, and (2) the difficulty of distinguishing concealed objects from the background, which arises from the intrinsic similarities in concealed scenarios. In this paper, we introduce the first unified method for ISCOS to address these challenges. To tackle the issue of incomplete supervision, we propose a unified mean-teacher framework, SEE, that leverages the vision foundation model, ``\emph{Segment Anything Model (SAM)}'', to generate pseudo-labels using coarse masks produced by the teacher model as prompts. To mitigate the effect of low-quality segmentation masks, we introduce a series of strategies for pseudo-label generation, storage, and supervision. These strategies aim to produce informative pseudo-labels, store the best pseudo-labels generated, and select the most reliable components to guide the student model, thereby ensuring robust network training. Additionally, to tackle the issue of intrinsic similarity, we design a hybrid-granularity feature grouping module that groups features at different granularities and aggregates these results. By clustering similar features, this module promotes segmentation coherence, facilitating more complete segmentation for both single-object and multiple-object images. We validate the effectiveness of our approach across multiple ISCOS tasks, and experimental results demonstrate that our method achieves state-of-the-art performance. Furthermore, SEE can serve as a plug-and-play solution, enhancing the performance of existing models.
title Segment Concealed Objects with Incomplete Supervision
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2506.08955