Magnification-Aware Distillation (MAD): A Self-Supervised Framework for Unified Representation Learning in Gigapixel Whole-Slide Images

• URL: http://arxiv.org/abs/2512.14796v1
• Date: Tue, 16 Dec 2025 15:47:45 GMT
• Title: Magnification-Aware Distillation (MAD): A Self-Supervised Framework for Unified Representation Learning in Gigapixel Whole-Slide Images
• Abstract summary: Whole-slide images (WSIs) contain tissue information distributed across multiple magnification levels.<n>Most self-supervised models treat these scales as independent views.<n>This study introduces Magni-Aware Distillation (MAD), a self-supervised strategy that links low-magnification context with spatially aligned high-magnification detail.
• Score: 0.8425266163142465
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Whole-slide images (WSIs) contain tissue information distributed across multiple magnification levels, yet most self-supervised methods treat these scales as independent views. This separation prevents models from learning representations that remain stable when resolution changes, a key requirement for practical neuropathology workflows. This study introduces Magnification-Aware Distillation (MAD), a self-supervised strategy that links low-magnification context with spatially aligned high-magnification detail, enabling the model to learn how coarse tissue structure relates to fine cellular patterns. The resulting foundation model, MAD-NP, is trained entirely through this cross-scale correspondence without annotations. A linear classifier trained only on 10x embeddings maintains 96.7% of its performance when applied to unseen 40x tiles, demonstrating strong resolution-invariant representation learning. Segmentation outputs remain consistent across magnifications, preserving anatomical boundaries and minimizing noise. These results highlight the feasibility of scalable, magnification-robust WSI analysis using a unified embedding space

Related papers

• Domain-Specific Self-Supervised Representation Learning for Retinal Fundus Classification [0.0]
  Self-supervised learning has emerged as a promising alternative for learning useful representations from unlabeled data.<n>In this work, we investigate two SSL frameworks, SimSiam and SimCLR, for retinal disease classification from fundus images.<n>We show that tailoring augmentation strategies to the characteristics of retinal images plays a critical role in improving performance.
  arXiv  Detail & Related papers  (2026-08-27T06:44:04Z)
• One Model to Magnify Them All: Efficient Scale-Invariant Histopathology via Conditional Normalization and Continuous Magnification Training [2.519619892651923]
  Deep learning models are sensitive to scale variation.<n>We propose Conditional Normalization (CLN), a mechanism that generates affine parameters from pixel size via small pixel sizes.<n>On the PANDA prostate cancer dataset, our approach matches or independently trained single-magnification models and ranks among the top three performers at every evaluated magnification.
  arXiv  Detail & Related papers  (2026-08-10T10:28:43Z)
• Efficient Semi-Automated Material Microstructure Analysis Using Deep Learning: A Case Study in Additive Manufacturing [0.0]
  We present a semi-automated active learning based segmentation that integrates a U-Net based convolutional neural network with an interactive user annotation and correction interface.<n>The proposed framework reduces labeling effort while maintaining scalability and robustness and is broadly applicable to image based analysis across diverse materials systems.
  arXiv  Detail & Related papers  (2026-03-14T08:28:00Z)
• Did Models Sufficient Learn? Attribution-Guided Training via Subset-Selected Counterfactual Augmentation [61.248535801314375]
  Subset-Selected Counterfactual Augmentation (SS-CA)<n>We develop Counterfactual LIMA to identify minimal spatial region sets whose removal can selectively alter model predictions.<n>Experiments show that SS-CA improves generalization on in-distribution (ID) test data and achieves superior performance on out-of-distribution (OOD) benchmarks.
  arXiv  Detail & Related papers  (2025-11-15T08:39:22Z)
• UHKD: A Unified Framework for Heterogeneous Knowledge Distillation via Frequency-Domain Representations [5.382357091398666]
  Unified Heterogeneous Knowledge Distillation (UHKD) is proposed as a framework that leverages intermediate features in the frequency domain for cross-architecture transfer.<n>Experiments on CIFAR-100 and ImageNet-1K demonstrate gains of 5.59% and 0.83% over the latest method.
  arXiv  Detail & Related papers  (2025-10-28T06:41:43Z)
• DiSSECT: Structuring Transfer-Ready Medical Image Representations through Discrete Self-Supervision [9.254163621425727]
  DiSSECT is a framework that integrates multi-scale vector quantization into the SSL pipeline to impose a discrete representational bottleneck.<n>It achieves strong performance on both classification and segmentation tasks, requiring minimal or no fine-tuning.<n>We validate DiSSECT across multiple public medical imaging datasets, demonstrating its robustness and generalizability.
  arXiv  Detail & Related papers  (2025-09-23T07:58:21Z)
• PathSegDiff: Pathology Segmentation using Diffusion model representations [63.20694440934692]
  We propose PathSegDiff, a novel approach for histopathology image segmentation that leverages Latent Diffusion Models (LDMs) as pre-trained featured extractors.<n>Our method utilizes a pathology-specific LDM, guided by a self-supervised encoder, to extract rich semantic information from H&E stained histopathology images.<n>Our experiments demonstrate significant improvements over traditional methods on the BCSS and GlaS datasets.
  arXiv  Detail & Related papers  (2025-04-09T14:58:21Z)
• Fuse Before Transfer: Knowledge Fusion for Heterogeneous Distillation [52.0297393822012]
  We introduce an assistant model as a bridge to facilitate smooth feature knowledge transfer between heterogeneous teachers and students.<n>Within our proposed design principle, the assistant model combines the advantages of cross-architecture inductive biases and module functions.<n>Our proposed method is evaluated across some homogeneous model pairs and arbitrary heterogeneous combinations of CNNs, ViTs, spatial KDs.
  arXiv  Detail & Related papers  (2024-10-16T08:02:49Z)
• Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think [72.48325960659822]
  One main bottleneck in training large-scale diffusion models for generation lies in effectively learning these representations.<n>We study this by introducing a straightforward regularization called REPresentation Alignment (REPA), which aligns the projections of noisy input hidden states in denoising networks with clean image representations obtained from external, pretrained visual encoders.<n>The results are striking: our simple strategy yields significant improvements in both training efficiency and generation quality when applied to popular diffusion and flow-based transformers, such as DiTs and SiTs.
  arXiv  Detail & Related papers  (2024-10-09T14:34:53Z)
• Attention-guided Feature Distillation for Semantic Segmentation [8.344263189293578]
  This paper showcases the efficacy of a simple yet powerful method for utilizing refined feature maps to transfer attention.<n>The proposed Attention-guided Feature Distillation (AttnFD) method, employs the Convolutional Block Attention Module (CBAM)<n>It achieves state-of-the-art results in terms of improving the mean Intersection over Union (mIoU) of the student network on the PascalVoc 2012, Cityscapes, COCO, and CamVid datasets.
  arXiv  Detail & Related papers  (2024-03-08T16:57:47Z)
• Continual Vision-Language Representation Learning with Off-Diagonal Information [112.39419069447902]
  Multi-modal contrastive learning frameworks like CLIP typically require a large amount of image-text samples for training. This paper discusses the feasibility of continual CLIP training using streaming data.
  arXiv  Detail & Related papers  (2023-05-11T08:04:46Z)
• Multiscale Structure Guided Diffusion for Image Deblurring [24.09642909404091]
  Diffusion Probabilistic Models (DPMs) have been employed for image deblurring. We introduce a simple yet effective multiscale structure guidance as an implicit bias. We demonstrate more robust deblurring results with fewer artifacts on unseen data.
  arXiv  Detail & Related papers  (2022-12-04T10:40:35Z)
• Efficient Self-Supervision using Patch-based Contrastive Learning for Histopathology Image Segmentation [0.456877715768796]
  We propose a framework for self-supervised image segmentation using contrastive learning on image patches. A fully convolutional neural network (FCNN) is trained in a self-supervised manner to discern features in the input images. The proposed model only consists of a simple FCNN with 10.8k parameters and requires about 5 minutes to converge on the high resolution microscopy datasets.
  arXiv  Detail & Related papers  (2022-08-23T07:24:47Z)
• Learning Deformable Image Registration from Optimization: Perspective, Modules, Bilevel Training and Beyond [62.730497582218284]
  We develop a new deep learning based framework to optimize a diffeomorphic model via multi-scale propagation. We conduct two groups of image registration experiments on 3D volume datasets including image-to-atlas registration on brain MRI data and image-to-image registration on liver CT data.
  arXiv  Detail & Related papers  (2020-04-30T03:23:45Z)

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.