mlsanityData to 14 Oct 2026

PraNet-V2: Dual-Supervised Reverse Attention for Medical Image Segmentation

arXiv 2504.10986 ↗First posted 15 Apr 2025cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Accurate medical image segmentation is essential for effective diagnosis and treatment. Previously, PraNet-V1 was proposed to enhance polyp segmentation by introducing a reverse attention (RA) module that utilizes background information. However, PraNet-V1 struggles with multi-class segmentation tasks. To address this limitation, we propose PraNet-V2, which, compared to PraNet-V1, effectively performs a broader range of tasks including multi-class segmentation. At the core of PraNet-V2 is the Dual-Supervised Reverse Attention (DSRA) module, which incorporates explicit background supervision, independent background modeling, and semantically enriched attention fusion. Our PraNet-V2 framework demonstrates strong performance on four polyp segmentation datasets. Additionally, by integrating DSRA to iteratively enhance foreground segmentation results in three state-of-the-art semantic segmentation models, we achieve up to a 1.36% improvement in mean Dice score. Code is available at: https://github.com/ai4colonoscopy/PraNet-V2/tree/main/binary_seg/jittor.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 29 of its 38 references that are in the map. First posted on arXiv 15 Apr 2025.

Builds on

29 of 38 references.

References · 29

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  3. 2021TransUNet: Transformers Make Strong Encoders for Medical Image Segmentationcited by 1,558
  4. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,476
  5. 2018Attention U-Net: Learning Where to Look for the Pancreascited by 1,435
  6. 2021Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentationcited by 1,222
  7. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 751
  8. 2019Kvasir-SEG: A Segmented Polyp Datasetcited by 589
  9. 2019UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentationcited by 586
  10. 2017Structure-measure: A New Way to Evaluate Foreground Mapscited by 480
  11. 2019Res2Net: A New Multi-scale Backbone Architecturecited by 470
  12. 2020PraNet: Parallel Reverse Attention Network for Polyp Segmentationcited by 460
17 more
  1. 2018Enhanced-alignment Measure for Binary Foreground Map Evaluationcited by 370
  2. 2020UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentationcited by 332
  3. 2016A Benchmark for Endoluminal Scene Segmentation of Colonoscopy Imagescited by 221
  4. 2021nnFormer: Interleaved Transformer for Volumetric Segmentationcited by 180
  5. 2021Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformerscited by 159
  6. 2024EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentationcited by 64
  7. 2021UACANet: Uncertainty Augmented Context Attention for Polyp Segmentationcited by 61
  8. 2022Stepwise Feature Fusion: Local Guides Globalcited by 56
  9. 2023One-Prompt to Segment All Medical Imagescited by 38
  10. 2023Multi-scale Hierarchical Vision Transformer with Cascaded Attention Decoding for Medical Image Segmentationcited by 34
  11. 2024LKM-UNet: Large Kernel Vision Mamba UNet for Medical Image Segmentationcited by 34
  12. 2024Open-World Semantic Segmentation Including Class Similaritycited by 24
  13. 2024SelfReg-UNet: Self-Regularized UNet for Medical Image Segmentationcited by 18
  14. 2024Frontiers in Intelligent Colonoscopycited by 14
  15. 2023MIST: Medical Image Segmentation Transformer with Convolutional Attention Mixing (CAM) Decodercited by 12
  16. 2024ASPS: Augmented Segment Anything Model for Polyp Segmentationcited by 12
  17. 2023Polyper: Boundary Sensitive Polyp Segmentationcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2026SurgMotion: A Video-Native Foundation Model for Universal Understanding of Surgical Videoscited by 4
  2. 2026DiSa: Saliency-Aware Foreground-Background Disentangled Framework for Open-Vocabulary Semantic Segmentationcited by 2
  3. 2025MicroAUNet: Boundary-Enhanced Multi-scale Fusion with Knowledge Distillation for Colonoscopy Polyp Image Segmentationcited by 0
  4. 2026MedCAGD: Context-Aware Gated Decoder for Efficient Medical Image Segmentationcited by 0