mlsanityData to 14 Oct 2026

M3D-Net: Hierarchical Coordination of Spatial Context, Feature Reuse, and Differential Attention for Mammography Classification

arXiv 2609.27523 ↗First posted 23 Sep 2026cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Breast image classification requires local detail and global tissue context, yet these cues can weaken as representations deepen. We present M3D-Net, a mammography encoder that hierarchically coordinates multi-scale coordinate attention, bounded dynamic feature reuse, and differential attention through resolution-aware operator placement. Within-stage retrieval preserves access to earlier features, coordinate-aware aggregation integrates local and global context, and differential attention operates at coarse resolutions. We evaluate image-only classification on AISSLab mammography and an adapted image--clinical model on BrEaST ultrasound. Against EdgeNeXt, RepViT, and TransXNet, the proposed implementations achieve the highest recorded validation accuracy and late-training accuracy, with the lowest endpoint cross-entropy loss. Validation accuracies reach 97.78% and 80.39%, respectively. These results support further evaluation of hierarchical coordination across breast imaging settings; repeated-seed, component-controlled, and independent evaluations remain necessary.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 16 of its 24 references that are in the map. First posted on arXiv 23 Sep 2026.

Builds on

16 of 24 references.

References · 16

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Densely Connected Convolutional Networkscited by 6,720
  3. 2017On Calibration of Modern Neural Networkscited by 4,960
  4. 2016Pyramid Scene Parsing Networkcited by 2,479
  5. 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 931
  6. 2018Confounding variables can degrade generalization performance of radiological deep learning modelscited by 379
  7. 2021Coordinate Attention for Efficient Mobile Network Designcited by 241
  8. 2023RepViT: Revisiting Mobile CNN From ViT Perspectivecited by 123
  9. 2022EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applicationscited by 121
  10. 2019Deep Neural Networks Improve Radiologists' Performance in Breast Cancer Screeningcited by 95
  11. 2017End-to-end Training for Whole Image Breast Cancer Diagnosis using An All Convolutional Designcited by 88
  12. 2025MUDDFormer: Breaking Residual Bottlenecks in Transformers via Multiway Dynamic Dense Connectionscited by 31
4 more
  1. 2019Robust breast cancer detection in mammography and digital breast tomosynthesis using annotation-efficient deep learning approachcited by 27
  2. 2017High-Resolution Breast Cancer Screening with Multi-View Deep Convolutional Neural Networkscited by 25
  3. 2023TransXNet: Learning Both Global and Local Dynamics with a Dual Dynamic Token Mixer for Visual Recognitioncited by 21
  4. 2026Attend what matters: Leveraging vision foundational models for breast cancer classification using mammogramscited by 1

Built on by

Not cited yet.