mlsanityData to 14 Oct 2026

Stepwise Feature Fusion: Local Guides Global

arXiv 2203.03635 ↗First posted 7 Mar 2022eess.IV cs.CVcited by 56

Not on the map. Why?

Abstract (arXiv)

Colonoscopy, currently the most efficient and recognized colon polyp detection technology, is necessary for early screening and prevention of colorectal cancer. However, due to the varying size and complex morphological features of colonic polyps as well as the indistinct boundary between polyps and mucosa, accurate segmentation of polyps is still challenging. Deep learning has become popular for accurate polyp segmentation tasks with excellent results. However, due to the structure of polyps image and the varying shapes of polyps, it easy for existing deep learning models to overfitting the current dataset. As a result, the model may not process unseen colonoscopy data. To address this, we propose a new State-Of-The-Art model for medical image segmentation, the SSFormer, which uses a pyramid Transformer encoder to improve the generalization ability of models. Specifically, our proposed Progressive Locality Decoder can be adapted to the pyramid Transformer backbone to emphasize local features and restrict attention dispersion. The SSFormer achieves statet-of-the-art performance in both learning and generalization assessment.

Key facts. Cited by 56 papers in the map (data through 14 Oct 2026). Builds on 19 of its 26 references that are in the map. First posted on arXiv 7 Mar 2022.

Builds on

19 of 26 references.

References · 19

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  5. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  6. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
  7. 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,525
  8. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,369
  9. 2021CvT: Introducing Convolutions to Vision Transformerscited by 947
  10. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 751
  11. 2021Do Vision Transformers See Like Convolutional Neural Networks?cited by 675
  12. 2019Kvasir-SEG: A Segmented Polyp Datasetcited by 589
7 more
  1. 2017Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC)cited by 549
  2. 2020PraNet: Parallel Reverse Attention Network for Polyp Segmentationcited by 460
  3. 2021Intriguing Properties of Vision Transformerscited by 446
  4. 2021DeepViT: Towards Deeper Vision Transformercited by 289
  5. 2021UACANet: Uncertainty Augmented Context Attention for Polyp Segmentationcited by 61
  6. 2021MSRF-Net: A Multi-Scale Residual Fusion Network for Biomedical Image Segmentationcited by 53
  7. 2021SimViT: Exploring a Simple Vision Transformer with sliding windowscited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 5; 2023: 11; 2024: 22; 2025: 16; 2026: 2.

56 papers.

Sort:

By area:

  1. 2024EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentationcited by 64
  2. 2022FCN-Transformer Feature Fusion for Polyp Segmentationcited by 37
  3. 2023Multi-scale Hierarchical Vision Transformer with Cascaded Attention Decoding for Medical Image Segmentationcited by 34
  4. 2023Using DUCK-Net for Polyp Image Segmentationcited by 31
  5. 2025MMRC: A Large-Scale Benchmark for Understanding Multimodal Large Language Model in Real-World Conversationcited by 29
  6. 2024Segment Any Cell: A SAM-based Auto-prompting Fine-tuning Framework for Nuclei Segmentationcited by 24
  7. 2022DuAT: Dual-Aggregation Transformer Network for Medical Image Segmentationcited by 22
  8. 2023CamoDiffusion: Camouflaged Object Detection via Conditional Diffusion Modelscited by 21
  9. 2023WeakPolyp: You Only Look Bounding Box for Polyp Segmentationcited by 21
  10. 2023G-CASCADE: Efficient Cascaded Graph Convolutional Decoding for 2D Medical Image Segmentationcited by 21
  11. 2024Stable Diffusion Segmentation for Biomedical Images with Single-step Reverse Processcited by 16
  12. 2024On Efficient Variants of Segment Anything Model: A Surveycited by 16
38 more
  1. 2024Frontiers in Intelligent Colonoscopycited by 14
  2. 2023A Survey on Deep Learning for Polyp Segmentation: Techniques, Challenges and Future Trendscited by 12
  3. 2024Contextrast: Contextual Contrastive Learning for Semantic Segmentationcited by 12
  4. 2024ASPS: Augmented Segment Anything Model for Polyp Segmentationcited by 12
  5. 2022ESFPNet: efficient deep learning architecture for real-time lesion segmentation in autofluorescence bronchoscopic videocited by 11
  6. 2023Attention Mechanisms in Medical Image Segmentation: A Surveycited by 9
  7. 2024MoRe: Class Patch Attention Needs Regularization for Weakly Supervised Semantic Segmentationcited by 9
  8. 2026EEO-TFV: Escape-Explore Optimizer for Web-Scale Time-Series Forecasting and Vision Analysiscited by 9
  9. 2024Polyp SAM 2: Advancing Zero shot Polyp Segmentation in Colorectal Cancer Detectioncited by 8
  10. 2024SAM-SP: Self-Prompting Makes SAM Great Againcited by 8
  11. 2022PatchRefineNet: Improving Binary Segmentation by Incorporating Signals from Optimal Patch-wise Binarizationcited by 6
  12. 2024Self-Prompting Polyp Segmentation in Colonoscopy using Hybrid Yolo-SAM 2 Modelcited by 6
  13. 2024Colorectal Polyp Segmentation in the Deep Learning Era: A Comprehensive Surveycited by 5
  14. 2024Polyp-DAM: Polyp segmentation via depth anything modelcited by 5
  15. 2024Trans2Unet: Neural fusion for Nuclei Semantic Segmentationcited by 5
  16. 2023Pyramid Pixel Context Adaption Network for Medical Image Classification with Supervised Contrastive Learningcited by 4
  17. 2025PraNet-V2: Dual-Supervised Reverse Attention for Medical Image Segmentationcited by 4
  18. 2023Medical Image Segmentation via Sparse Coding Decodercited by 3
  19. 2024ProMISe: Promptable Medical Image Segmentation using SAMcited by 3
  20. 2024Adaptation of Distinct Semantics for Uncertain Areas in Polyp Segmentationcited by 3
  21. 2025LGPS: A Lightweight GAN-Based Approach for Polyp Segmentation in Colonoscopy Imagescited by 3
  22. 2025PolypSegTrack: Unified Foundation Model for Colonoscopy Video Analysiscited by 3
  23. 2025Diffusion-Based Data Augmentation for Medical Image Segmentationcited by 3
  24. 2022LAPFormer: A Light and Accurate Polyp Segmentation Transformercited by 2
  25. 2024EFCNet: Every Feature Counts for Small Medical Object Segmentationcited by 2
  26. 2025FedSemiDG: Domain Generalized Federated Semi-supervised Medical Image Segmentationcited by 2
  27. 2025Marine Saliency Segmenter: Object-Focused Conditional Diffusion with Region-Level Semantic Knowledge Distillationcited by 2
  28. 2025WoundAmbit: Bridging State-of-the-Art Semantic Segmentation and Real-World Wound Carecited by 2
  29. 2024HiFiSeg: High-Frequency Information Enhanced Polyp Segmentation with Global-Local Vision Transformercited by 1
  30. 2025An Efficient Dual-Line Decoder Network with Multi-Scale Convolutional Attention for Multi-organ Segmentationcited by 1
  31. 2025Dual Interaction Network with Cross-Image Attention for Medical Image Segmentationcited by 1
  32. 2025LoMix: Learnable Weighted Multi-Scale Logits Mixing for Medical Image Segmentationcited by 1
  33. 2023Prototype Learning for Out-of-Distribution Polyp Segmentationcited by 0
  34. 2023FLDNet: A Foreground-Aware Network for Polyp Segmentation Leveraging Long-Distance Dependenciescited by 0
  35. 2024Polyp segmentation in colonoscopy images using DeepLabV3++cited by 0
  36. 2024An Effective UNet Using Feature Interaction and Fusion for Organ Segmentation in Medical Imagecited by 0
  37. 2024MixPolyp: Integrating Mask, Box and Scribble Supervision for Enhanced Polyp Segmentationcited by 0
  38. 2024Polyp-SES: Automatic Polyp Segmentation with Self-Enriched Semantic Modelcited by 0

50 most cited of 56 All 56 (JSON)