mlsanityData to 14 Oct 2026

SAGE: Shape-Adapting Gated Experts for Adaptive Histopathology Image Segmentation

arXiv 2511.18493 ↗First posted 23 Nov 2025eess.IV cs.AI cs.CVcited by 1

On the map: Mixture-of-experts → Medical and biomedical MoE

Abstract (arXiv)

The significant variability in cell size and shape continues to pose a major obstacle in computer-assisted cancer detection on gigapixel Whole Slide Images (WSIs), due to cellular heterogeneity. Current CNN-Transformer hybrids use static computation graphs with fixed routing. This leads to extra computation and makes it harder to adapt to changes in input. We propose Shape-Adapting Gated Experts (SAGE), an input-adaptive framework that enables dynamic expert routing in heterogeneous visual networks. SAGE reconfigures static backbones into dynamically routed expert architectures via a dual-path design with hierarchical gating and a Shape-Adapting Hub (SA-Hub) that harmonizes feature representations across convolutional and transformer modules. Embodied as SAGE with ConvNeXt and Vision Transformer UNet (SAGE-ConvNeXt+ViT-UNet), our model achieves a Dice score of 95.23% on EBHI, DSC scores of 92.78% and 91.42% on GlaS Test A and Test B, respectively, and 91.26% DSC at the WSI level on DigestPath, while exhibiting robust generalization under distribution shifts by adaptively balancing local refinement and global context. SAGE establishes a scalable foundation for dynamic expert routing in visual networks, thereby facilitating flexible visual reasoning. Project page: https://oxyzgiahuy.github.io/sage/

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Medical and biomedical MoE, one of 12 directions in Mixture-of-experts. Builds on 23 of its 37 references that are in the map. First posted on arXiv 23 Nov 2025.

Builds on

23 of 37 references.

References · 23

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  5. 2022A ConvNet for the 2020scited by 3,579
  6. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  7. 2021TransUNet: Transformers Make Strong Encoders for Medical Image Segmentationcited by 1,558
  8. 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,525
  9. 2018Attention U-Net: Learning Where to Look for the Pancreascited by 1,435
  10. 2021Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentationcited by 1,222
  11. 2021Transformers in Vision: A Surveycited by 1,013
  12. 2024U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentationcited by 419
11 more
  1. 2021UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-wise Perspective with Transformercited by 197
  2. 2024Swin-UMamba: Mamba-based UNet with ImageNet-based pretrainingcited by 179
  3. 2021TransAttUnet: Multi-level Attention-guided U-Net with Transformer for Medical Image Segmentationcited by 60
  4. 2024Multi-Task Dense Prediction via Mixture of Low-Rank Expertscited by 58
  5. 2017Choosing Smartly: Adaptive Multimodal Fusion for Object Detection in Changing Environmentscited by 34
  6. 2024Sigmoid Gating is More Sample Efficient than Softmax Gating in Mixture of Expertscited by 24
  7. 2024SelfReg-UNet: Self-Regularized UNet for Medical Image Segmentationcited by 18
  8. 2022EBHI-Seg: A Novel Enteroscope Biopsy Histopathological Haematoxylin and Eosin Image Dataset for Image Segmentation Taskscited by 15
  9. 2020Multi-level colonoscopy malignant tissue detection with adversarial CAC-UNetcited by 6
  10. 2024EViT-Unet: U-Net Like Efficient Vision Transformer for Medical Image Segmentation on Mobile and Edge Devicescited by 6
  11. 2025MoLEx: Mixture of Layer Experts for Finetuning with Sparse Upcyclingcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026φ-Balancing for Mixture-of-Experts Trainingcited by 5

Similar, not cited

Close in wording, no citation either way

  1. 2026DeepHistoViT: An Interpretable Vision Transformer Framework for Histopathological Cancer Classification
  2. 2026Computationally Efficient Pathology Segmentation using Knowledge Distillation from Foundation Models
  3. 2026Dual-Adaptive SAM3: Hierarchical Routing over Low-Rank Expert Layers for Parameter-Efficient Medical Image Segmentation
  4. 2026From UNI2-h to ConvNeXt-T: Lightweight Nuclei Instance Segmentation via Knowledge Distillation
  5. 2025Semi-MoE: Mixture-of-Experts meets Semi-Supervised Histopathology Segmentation
  6. 2022Unsupervised Domain Adaptation through Shape Modeling for Medical Image Segmentation
  7. 2022Self-Supervised Vision Transformers Learn Visual Concepts in Histopathology
  8. 2026Region-Graph Optimal Transport Routing for Mixture-of-Experts Whole-Slide Image Classification