paper-with-me

Papers

Concealed Object Segmentation with Hierarchical Coherence Modeling

2024-01-22 · Fengyang Xiao, Pan Zhang, Chunming He, Runze Hu, Yutao Liu

Concealed object segmentation (COS) is a challenging task that involves localizing and segmenting those concealed objects that are visually blended with their surrounding environments. Despite achieving remarkable success, existing COS segmenters still struggle to achieve complete segmentation results in extremely concealed scenarios. In this paper, we propose a Hierarchical Coherence Modeling (HCM) segmenter for COS, aiming to address this incomplete segmentation limitation. In specific, HCM promotes feature coherence by leveraging the intra-stage coherence and cross-stage coherence modules, exploring feature correlations at both the single-stage and contextual levels. Additionally, we introduce the reversible re-calibration decoder to detect previously undetected parts in low-confidence regions, resulting in further enhancing segmentation performance. Extensive experiments conducted on three COS tasks, including camouflaged object detection, polyp image segmentation, and transparent object detection, demonstrate the promising results achieved by the proposed HCM segmenter.

📄 PDF Abstract BibTeX arXiv:2401.11767

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderImage SegmentationObjectobject-detectionObject DetectionSegmentationSemantic SegmentationTransparent Object Detection

Similar Papers 제목 키워드 기반

Weakly-Supervised Concealed Object Segmentation with SAM-based Pseudo Labeling and Multi-scale Feature Grouping

2023-05-18 · NeurIPS 2023 11 · Chunming He, Kai Li, Yachao Zhang, Guoxia Xu 외

Weakly-Supervised Concealed Object Segmentation (WSCOS) aims to segment objects well blended with surrounding environments using sparsely-annotated data for model training. It remains a challenging task since (1) it is h…

SegmentationSemantic Segmentation

Segment Concealed Objects with Incomplete Supervision

2025-06-10 · Chunming He, Kai Li, Yachao Zhang, Ziyun Yang 외

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-annotation…

Pseudo LabelSegmentationSemantic Segmentation

Two-Level Transformer and Auxiliary Coherence Modeling for Improved Text Segmentation

2020-01-03 · Goran Glavaš, Swapna Somasundaran

Breaking down the structure of long texts into semantically coherent segments makes the texts more readable and supports downstream applications like summarization and retrieval. Starting from an apparent link between te…

Cross-Lingual Word EmbeddingsMulti-Task LearningRetrievalSegmentation+4

Nested Unfolding Network for Real-World Concealed Object Segmentation

2025-11-22 · Chunming He, Rihan Zhang, Dingming Zhang, Fengyang Xiao 외 arxiv

Deep unfolding networks (DUNs) have recently advanced concealed object segmentation (COS) by modeling segmentation as iterative foreground-background separation. However, existing DUN-based methods (RUN) inherently coupl…

Object SegmentationImage Restoration

Concealed Object Detection

2021-02-20 · Deng-Ping Fan, Ge-Peng Ji, Ming-Ming Cheng, Ling Shao

We present the first systematic study on concealed object detection (COD), which aims to identify objects that are "perfectly" embedded in their background. The high intrinsic similarities between the concealed objects a…

Camouflaged Object SegmentationDichotomous Image SegmentationObjectobject-detection+1