Sharpening Lightweight Models for Generalized Polyp Segmentation: A Boundary Guided Distillation from Foundation Models

• URL: http://arxiv.org/abs/2604.17865v1
• Date: Mon, 20 Apr 2026 06:25:06 GMT
• Title: Sharpening Lightweight Models for Generalized Polyp Segmentation: A Boundary Guided Distillation from Foundation Models
• Abstract summary: polyp segmentation is critical for early colorectal cancer detection and its prevention, yet remains challenging due to weak boundaries, large appearance variations, and limited annotated data.<n>We propose LiteBounD, a framework that transfers semantic and structural priors from multiple Vision Foundation Models into compact segmentation backbones.<n>LiteBounD consistently outperforms its lightweight baselines by a significant margin and performance competitive with state-of-the-art methods.
• Score: 5.836991649815995
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Automated polyp segmentation is critical for early colorectal cancer detection and its prevention, yet remains challenging due to weak boundaries, large appearance variations, and limited annotated data. Lightweight segmentation models such as U-Net, U-Net++, and PraNet offer practical efficiency for clinical deployment but struggle to capture the rich semantic and structural cues required for accurate delineation of complex polyp regions. In contrast, large Vision Foundation Models (VFMs), including SAM, OneFormer, Mask2Former, and DINOv2, exhibit strong generalization but transfer poorly to polyp segmentation due to domain mismatch, insufficient boundary sensitivity, and high computational cost. To bridge this gap, we propose \textit{\textbf{LiteBounD}, a \underline{Li}gh\underline{t}w\underline{e}ight \underline{Boun}dary-guided \underline{D}istillation} framework that transfers complementary semantic and structural priors from multiple VFMs into compact segmentation backbones. LiteBounD introduces (i) a dual-path distillation mechanism that disentangles semantic and boundary-aware representations, (ii) a frequency-aware alignment strategy that supervises low-frequency global semantics and high-frequency boundary details separately, and (iii) a boundary-aware decoder that fuses multi-scale encoder features with distilled semantically rich boundary information for precise segmentation. Extensive experiments on both seen (Kvasir-SEG, CVC-ClinicDB) and unseen (ColonDB, CVC-300, ETIS) datasets demonstrate that LiteBounD consistently outperforms its lightweight baselines by a significant margin and achieves performance competitive with state-of-the-art methods, while maintaining the efficiency required for real-time clinical use. Our code is available at https://github.com/lostinrepo/LiteBounD.

Related papers

• When Simplicity Wins: Bottleneck-Aware Context Modeling for Lightweight Semantic Segmentation [58.325533783810016]
  We propose SiConMo, a lightweight yet effective framework for semantic segmentation.<n>We show that simplicity arises from a key design principle: at very low computational budgets, the bottleneck is the most efficient stage to integrate local and global context.<n> experiments on ADE20K, PASCAL Context, Cityscapes, and COCO-Stuff demonstrate that SiConMo achieves a state-of-the-art accuracy-efficiency trade-off.
  arXiv  Detail & Related papers  (2026-08-19T14:47:07Z)
• Douyin Multimodal Embedding Model Technical Report [77.9018834072698]
  Multimodal representation learning is a cornerstone of modern AI.<n>We present Douyin Multimodal Embedding (DME), a model trained in two stages to combine both strengths.
  arXiv  Detail & Related papers  (2026-08-03T12:31:49Z)
• Induce to Empower: Improving Lightweight Baselines via Foundation Model Induction for Generalized Polyp Segmentation [17.181959776318823]
  We propose Lite-Polyp Inductor (Lite-Pi), a novel foundation model induction framework that significantly enhances lightweight polyp segmentation baselines.<n>Our proposed framework generates FM-specific prototype representations and aligns them semantically with the corresponding foundation model priors.<n>Experiments across five polyp segmentation benchmark demonstrate that Lite- significantly improves lightweight baselines.
  arXiv  Detail & Related papers  (2026-07-19T11:57:19Z)
• TACoS: Weakly Supervised Learning of Two-Dimensional Materials from Scribble Annotations to Precise Segmentation [10.511271973672628]
  TACoS is a specialized segmentation framework tailored for 2D materials.<n>It integrates semi-supervised consistency learning with structured tree energy constraints.<n>It achieves over 96% of fully supervised performance using less than 0.6% annotated data.
  arXiv  Detail & Related papers  (2026-07-08T09:02:31Z)
• TGC-Net: A Structure-Aware and Semantically-Aligned Framework for Text-Guided Medical Image Segmentation [56.09179939570486]
  We propose TGC-Net, a CLIP-based framework focusing on parameter-efficient, task-specific adaptations.<n>TGC-Net achieves state-of-the-art performance with substantially fewer trainable parameters, including notable Dice gains on challenging benchmarks.
  arXiv  Detail & Related papers  (2025-12-24T12:06:26Z)
• From SAM to DINOv2: Towards Distilling Foundation Models to Lightweight Baselines for Generalized Polyp Segmentation [9.452022523459886]
  Polyp-DiFoM is a framework that transfers the rich representations of foundation models into lightweight segmentation baselines.<n>It consistently outperforms baseline models significantly, as well as the state-of-the-art model, with nearly 9 times reduced overhead.
  arXiv  Detail & Related papers  (2025-12-10T04:25:01Z)
• MicroAUNet: Boundary-Enhanced Multi-scale Fusion with Knowledge Distillation for Colonoscopy Polyp Image Segmentation [8.682943624128214]
  MicroAUNet is a light-weighted attention-based segmentation network that combines depthwise-separable dilated convolutions with a single-path, parameter-shared channel-spatial attention block.<n>Experiments on benchmarks demonstrate the state-of-the-art accuracy under extremely low model complexity, indicating that MicroAUNet is suitable for real-time clinical polyp segmentation.
  arXiv  Detail & Related papers  (2025-11-03T01:43:34Z)
• AURASeg: Attention Guided Upsampling with Residual Boundary-Assistive Refinement for Drivable-Area Segmentation [0.5729426778193399]
  We propose Attention-Guided Upsampling with Residual Boundary-Assistive Refinement (AURASeg) for semantic segmentation.<n>Our approach achieves an improvement in mean Intersection-over-Union (mIoU) of +1.26% and segmentation precision of +1.65% compared to state-of-the-art models.
  arXiv  Detail & Related papers  (2025-10-24T15:01:18Z)
• Hierarchical Self-Supervised Representation Learning for Depression Detection from Speech [51.14752758616364]
  Speech-based depression detection (SDD) is a promising, non-invasive alternative to traditional clinical assessments.<n>We propose HAREN-CTC, a novel architecture that integrates multi-layer SSL features using cross-attention within a multitask learning framework.<n>The model achieves state-of-the-art macro F1-scores of 0.81 on DAIC-WOZ and 0.82 on MODMA, outperforming prior methods across both evaluation scenarios.
  arXiv  Detail & Related papers  (2025-10-05T09:32:12Z)
• Unleashing Vision Foundation Models for Coronary Artery Segmentation: Parallel ViT-CNN Encoding and Variational Fusion [12.839049648094893]
  coronary artery segmentation is critical for computeraided diagnosis of coronary artery disease (CAD)<n>We propose a novel framework that leverages the power of vision foundation models (VFMs) through a parallel encoding architecture.<n>The proposed framework significantly outperforms state-of-the-art methods, achieving superior performance in accurate coronary artery segmentation.
  arXiv  Detail & Related papers  (2025-07-17T09:25:00Z)
• Mamba Guided Boundary Prior Matters: A New Perspective for Generalized Polyp Segmentation [3.075778955462259]
  Polyp segmentation in colonoscopy images is crucial for early detection and diagnosis of colorectal cancer.<n>We propose SAM-MaGuP, a groundbreaking approach for robust polyp segmentation.<n>By incorporating a boundary distillation module and a 1D-2D Mamba adapter within the Segment Anything Model (SAM), SAM-MaGuP excels at resolving weak boundary challenges.<n>Our key innovations, a Mamba-guided boundary prior and a 1D-2D Mamba block, set a new benchmark in the field, pushing the boundaries of polyp segmentation to new heights.
  arXiv  Detail & Related papers  (2025-07-02T09:16:58Z)
• Dual-scale Enhanced and Cross-generative Consistency Learning for Semi-supervised Medical Image Segmentation [49.57907601086494]
  Medical image segmentation plays a crucial role in computer-aided diagnosis. We propose a novel Dual-scale Enhanced and Cross-generative consistency learning framework for semi-supervised medical image (DEC-Seg)
  arXiv  Detail & Related papers  (2023-12-26T12:56:31Z)
• 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)
• BCS-Net: Boundary, Context and Semantic for Automatic COVID-19 Lung Infection Segmentation from CT Images [83.82141604007899]
  BCS-Net is a novel network for automatic COVID-19 lung infection segmentation from CT images. BCS-Net follows an encoder-decoder architecture, and more designs focus on the decoder stage. In each BCSR block, the attention-guided global context (AGGC) module is designed to learn the most valuable encoder features for decoder.
  arXiv  Detail & Related papers  (2022-07-17T08:54:07Z)
• The Devil is in the Boundary: Exploiting Boundary Representation for Basis-based Instance Segmentation [85.153426159438]
  We propose Basis based Instance(B2Inst) to learn a global boundary representation that can complement existing global-mask-based methods. Our B2Inst leads to consistent improvements and accurately parses out the instance boundaries in a scene.
  arXiv  Detail & Related papers  (2020-11-26T11:26:06Z)

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.