mlsanityData to 14 Oct 2026

Reload-Mamba: Hierarchical Anti-Dilution State-Space Modeling for Multi-Class Semantic Segmentation

arXiv 2606.17966 ↗First posted 16 Jun 2026cs.CVcited by 0

On the map: State-space sequence models (S4, Mamba) → Vision Mamba backbones

Abstract (arXiv)

Mamba-based state space models offer linear-time long-range modeling for high-resolution dense prediction, but sequential state-space propagation can attenuate boundary-sensitive and detail-sensitive responses that are critical in multi-class semantic segmentation. We propose Reload-Mamba, a semantic segmentation framework that addresses this propagation-induced response dilution through three segmentation-specific designs: (i) a boundary-supervised local detail prior that is explicitly trained with ground-truth boundary masks to identify regions requiring response restoration; (ii) a class-uncertainty-aware Reload Gate that incorporates per-pixel class entropy from a pre-reload auxiliary head as an additional gating signal, a formulation that is informative only under multi-class dense prediction; and (iii) a hierarchical multi-level Reload mechanism that applies anti-dilution refinement at three decoder levels and fuses the restored representations top-down. Built upon a ConvNeXt-Tiny encoder with a multi-scale decoder and four-directional Mamba scanning with pixel-wise directional attention, Reload-Mamba achieves 47.9% single-scale (48.9% multi-scale) mIoU on ADE20K and 83.2% single-scale mIoU on Cityscapes. With ResNet-101 + COCO pre-training under the standard DeepLab-style protocol, Reload-Mamba reaches 87.8% mIoU on PASCAL VOC 2012 val. Controlled ablations show that each of the three segmentation-specific designs contributes beyond a direct port of the prior anti-dilution architecture proposed for binarization, cumulatively improving over the direct-port baseline by +2.2 mIoU on ADE20K.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Vision Mamba backbones, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 37 of its 47 references that are in the map. First posted on arXiv 16 Jun 2026.

Builds on

37 of 47 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024Spatial-Mamba: Effective Visual State Space Models via Structure-aware State Fusion19 Oct
  2. 2024SparX: A Sparse Cross-Layer Connection Mechanism for Hierarchical Vision Mamba and Transformer Networks15 Sep
  3. 2024MambaVision: A Hybrid Mamba-Transformer Vision Backbone10 Jul
  4. 2024MambaOut: Do We Really Need Mamba for Vision?13 May
  5. 2024LocalMamba: Visual State Space Model with Windowed Selective Scan14 Mar
  6. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model17 Jan

Other references · 31

  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. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  6. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  7. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  8. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  9. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  10. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  11. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  12. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
19 more
  1. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  2. 2016Pyramid Scene Parsing Networkcited by 2,479
  3. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
  4. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
  5. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,487
  6. 2018Dual Attention Network for Scene Segmentationcited by 1,003
  7. 2018CCNet: Criss-Cross Attention for Semantic Segmentationcited by 718
  8. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 576
  9. 2014Deeply-Supervised Netscited by 367
  10. 2018Context Encoding for Semantic Segmentationcited by 290
  11. 2021Focal Self-attention for Local-Global Interactions in Vision Transformerscited by 288
  12. 2022SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentationcited by 252
  13. 2019Gated-SCNN: Gated Shape CNNs for Semantic Segmentationcited by 166
  14. 2019Expectation-Maximization Attention Networks for Semantic Segmentationcited by 147
  15. 2020Semantic Flow for Fast and Accurate Scene Parsingcited by 128
  16. 2018Learning a Discriminative Feature Network for Semantic Segmentationcited by 114
  17. 2019Boundary-Aware Feature Propagation for Scene Segmentationcited by 107
  18. 2020Tensor Low-Rank Reconstruction for Semantic Segmentationcited by 29
  19. 2026DeepMine-Mamba: Mitigating Information Dilution in Mamba-Based State Space Models for Document Image Binarizationcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Mamba2D: A Natively Multi-Dimensional State-Space Model for Vision Tasks
  2. 2024MTMamba: Enhancing Multi-Task Dense Scene Understanding by Mamba-Based Decoders
  3. 2024Attention-Mamba: A Mamba-Enhanced Multi-Scale Parallel Inference Network for Medical Image Segmentation
  4. 2025Mamba as a Bridge: Where Vision Foundation Models Meet Vision Language Models for Domain-Generalized Semantic Segmentation
  5. 2025MambaVesselNet++: A Hybrid CNN-Mamba Architecture for Medical Image Segmentation
  6. 2024Sigma: Siamese Mamba Network for Multi-Modal Semantic Segmentation
  7. 2025UINO-FSS: Unifying Representation Learning and Few-shot Segmentation via Hierarchical Distillation and Mamba-HyperCorrelation
  8. 2026Breaking the Resource Wall: Geometry-Guided Sequence Modeling for Efficient Semantic Segmentation