FocusNet: Transformer-enhanced Polyp Segmentation with Local and Pooling Attention

• URL: http://arxiv.org/abs/2504.13597v1
• Date: Fri, 18 Apr 2025 09:59:26 GMT
• Title: FocusNet: Transformer-enhanced Polyp Segmentation with Local and Pooling Attention
• Abstract summary: Colonoscopy is vital in the early diagnosis of colorectal polyps.<n>Regular screenings can effectively prevent benign polyps from progressing to CRC.<n>We propose FocusNet, a Transformer-enhanced focus attention network to improve polyp segmentation.
• Score: 11.964732823289333
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Colonoscopy is vital in the early diagnosis of colorectal polyps. Regular screenings can effectively prevent benign polyps from progressing to CRC. While deep learning has made impressive strides in polyp segmentation, most existing models are trained on single-modality and single-center data, making them less effective in real-world clinical environments. To overcome these limitations, we propose FocusNet, a Transformer-enhanced focus attention network designed to improve polyp segmentation. FocusNet incorporates three essential modules: the Cross-semantic Interaction Decoder Module (CIDM) for generating coarse segmentation maps, the Detail Enhancement Module (DEM) for refining shallow features, and the Focus Attention Module (FAM), to balance local detail and global context through local and pooling attention mechanisms. We evaluate our model on PolypDB, a newly introduced dataset with multi-modality and multi-center data for building more reliable segmentation methods. Extensive experiments showed that FocusNet consistently outperforms existing state-of-the-art approaches with a high dice coefficients of 82.47% on the BLI modality, 88.46% on FICE, 92.04% on LCI, 82.09% on the NBI and 93.42% on WLI modality, demonstrating its accuracy and robustness across five different modalities. The source code for FocusNet is available at https://github.com/JunZengz/FocusNet.

Related papers

• CFGPNet: Cross-Attention-Based Fused Gradient Programmed Network Framework for Multispectral Object Detection [4.299007466612815]
  RGB--T object detection exploits the complementary strengths of visible and infrared imagery, supporting robust perception in low-light, adverse-weather, and complex multi-scale environments.<n>Existing methods still suffer from insufficient cross-modal interaction, unstable fusion from modality distribution gaps, and the high computational cost.<n>CFGPNet is proposed, a Cross-Attention-Based Fused Gradient Programmed Network framework for multispectral object detection.
  arXiv  Detail & Related papers  (2026-08-06T15:59:13Z)
• Cross-Layer Feature Self-Attention Module for Multi-Scale Object Detection [14.148258708632211]
  Cross-Layer Feature Self-Attention Module (CFSAM)<n>CFSAM holistically models both local and global dependencies within multi-scale feature maps.<n>When integrated into the SSD300 framework, CFSAM significantly boosts detection performance.
  arXiv  Detail & Related papers  (2025-10-16T14:25:21Z)
• MNet-SAt: A Multiscale Network with Spatial-enhanced Attention for Segmentation of Polyps in Colonoscopy [0.10995326465245926]
  We propose a novel Multiscale Network with Spatial-enhanced Attention (MNetSAt) for polyp segmentation in colonoscopy images.<n>This framework incorporates four key modules: Edge-Guided Feature Enrichment (EGFE), Multi-Scale Feature Aggregator (MSFA), and Spatial-Enhanced Attention (SEAt)<n>We evaluate MNet-SAt on the Kvasir-SEG and CVC-ClinicDB datasets, achieving Dice Similarity Coefficients of 96.61% and 98.60%, respectively.
  arXiv  Detail & Related papers  (2024-12-27T05:17:29Z)
• Multi-scale and Multi-path Cascaded Convolutional Network for Semantic Segmentation of Colorectal Polyps [0.0]
  The study introduces a novel framework for colorectal polyp segmentation named the Multi-Scale and Multi-Path Cascaded Convolution Network (MMCC-Net)<n> MMCC-Net integrates multi-scale and multi-path cascaded convolutional techniques and enhances feature aggregation through dual attention modules, skip connections, and a feature enhancer.<n>The proposed MMCC-Net was tested across six public datasets and compared against eight SOTA models to demonstrate its efficiency in polyp segmentation.
  arXiv  Detail & Related papers  (2024-12-03T13:27:51Z)
• Multi-scale Cascaded Large-Model for Whole-body ROI Segmentation [5.430156054316826]
  We propose an innovative cascaded network architecture called the Multi-scale Cascaded Fusing Network (MCFNet) MCFNet effectively captures complex multi-scale and multi-resolution features. We conduct experiments using the A6000 GPU on diverse datasets from 671 patients, including 36,131 image-mask pairs.
  arXiv  Detail & Related papers  (2024-11-23T11:39:06Z)
• PVAFN: Point-Voxel Attention Fusion Network with Multi-Pooling Enhancing for 3D Object Detection [59.355022416218624]
  integration of point and voxel representations is becoming more common in LiDAR-based 3D object detection. We propose a novel two-stage 3D object detector, called Point-Voxel Attention Fusion Network (PVAFN) PVAFN uses a multi-pooling strategy to integrate both multi-scale and region-specific information effectively.
  arXiv  Detail & Related papers  (2024-08-26T19:43:01Z)
• ASPS: Augmented Segment Anything Model for Polyp Segmentation [77.25557224490075]
  The Segment Anything Model (SAM) has introduced unprecedented potential for polyp segmentation. SAM's Transformer-based structure prioritizes global and low-frequency information. CFA integrates a trainable CNN encoder branch with a frozen ViT encoder, enabling the integration of domain-specific knowledge.
  arXiv  Detail & Related papers  (2024-06-30T14:55:32Z)
• Center Focusing Network for Real-Time LiDAR Panoptic Segmentation [58.1194137706868]
  A novel center focusing network (CFNet) is introduced to achieve accurate and real-time LiDAR panoptic segmentation. CFFE is proposed to explicitly understand the relationships between the original LiDAR points and virtual instance centers. Our CFNet outperforms all existing methods by a large margin and is 1.6 times faster than the most efficient method.
  arXiv  Detail & Related papers  (2023-11-16T01:52:11Z)
• Learnable Weight Initialization for Volumetric Medical Image Segmentation [66.3030435676252]
  We propose a learnable weight-based hybrid medical image segmentation approach. Our approach is easy to integrate into any hybrid model and requires no external training data. Experiments on multi-organ and lung cancer segmentation tasks demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2023-06-15T17:55:05Z)
• Lesion-aware Dynamic Kernel for Polyp Segmentation [49.63274623103663]
  We propose a lesion-aware dynamic network (LDNet) for polyp segmentation. It is a traditional u-shape encoder-decoder structure incorporated with a dynamic kernel generation and updating scheme. This simple but effective scheme endows our model with powerful segmentation performance and generalization capability.
  arXiv  Detail & Related papers  (2023-01-12T09:53:57Z)
• Multi-scale Network with Attentional Multi-resolution Fusion for Point Cloud Semantic Segmentation [2.964101313270572]
  We present a comprehensive point cloud semantic segmentation network that aggregates both local and global multi-scale information. We introduce an Angle Correlation Point Convolution module to effectively learn the local shapes of points. Third, inspired by HRNet which has excellent performance on 2D image vision tasks, we build an HRNet customized for point cloud to learn global multi-scale context.
  arXiv  Detail & Related papers  (2022-06-27T21:03:33Z)
• PraNet: Parallel Reverse Attention Network for Polyp Segmentation [155.93344756264824]
  We propose a parallel reverse attention network (PraNet) for accurate polyp segmentation in colonoscopy images. We first aggregate the features in high-level layers using a parallel partial decoder (PPD) In addition, we mine the boundary cues using a reverse attention (RA) module, which is able to establish the relationship between areas and boundary cues.
  arXiv  Detail & Related papers  (2020-06-13T08:13:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.