Hierarchical Spatio-Channel Clustering for Efficient Model Compression in Medical Image Analysis

• URL: http://arxiv.org/abs/2604.23375v1
• Date: Sat, 25 Apr 2026 16:46:59 GMT
• Title: Hierarchical Spatio-Channel Clustering for Efficient Model Compression in Medical Image Analysis
• Abstract summary: This paper proposes a low-rank compression framework for CNNs that exploits redundancy across spatial regions and channel activations.<n>It is evaluated on an AlexNet-based brain tumour MRI model and compared with Global SVD and Tucker decomposition under (8.21,mathrmG) and (6times) compression budgets.<n>Our method outperforms both baselines, reducing FLOPs from (8.21,mathrmG) to (1.55,mathrmG) ((81.1times) reduction
• Score: 3.0242335275001757
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Convolutional neural networks (CNNs) have become increasingly difficult to deploy in resource-constrained environments due to their large memory and computational requirements. Although low-rank compression methods can reduce this burden, most existing approaches compress spatial and channel redundancy independently and therefore do not fully exploit the localised structure within convolutional feature maps. This paper proposes a hierarchical spatio-channel low-rank compression framework for CNNs that exploits redundancy across spatial regions and channel activations. Unlike conventional methods, which apply a uniform decomposition across an entire layer, the proposed approach first partitions feature maps into spatial regions, then groups channels according to their co-activation patterns within each region, and finally applies rank-adaptive SVD to each resulting spatio-channel cluster. The method is evaluated on an AlexNet-based brain tumour MRI classification model and compared with Global SVD and Tucker decomposition under \(3\times\) and \(6\times\) compression budgets. Our method outperforms both baselines, reducing FLOPs from \(8.21\,\mathrm{G}\) to \(1.55\,\mathrm{G}\) (\(81.1\%\) reduction), achieving a \(1.38\times\) inference speed-up, and increasing classification accuracy from \(87.76\%\) to \(89.80\%\). The method also improves the macro \(F_1\)-score and performance on challenging classes such as meningioma. A hyper-parameter trade-off analysis demonstrates that the framework provides Pareto-optimal configurations, enabling control over the balance between compression and predictive performance. Moderate clustering with adaptive rank selection yields strong results. Bootstrap standard errors are reported for all classification metrics.

Related papers

• Overcoming critical slowing down in frustrated spin systems by learned multiscale sampling [4.567122178196833]
  Cluster algorithms are among the most successful MCMC methods for mitigating critical slowing down in statistical systems.<n>Here, we sidestep this fundamental limitation by learning rather than constructing the relevant clusters.<n>We show that learned multiscale sampling can overcome critical slowing down in frustrated systems for which conventional cluster algorithms fail.
  arXiv  Detail & Related papers  (2026-08-31T17:21:54Z)
• MIS-HCC: Hierarchical Channel Clustering for Efficient Medical Image Segmentation [9.907733372150625]
  Medical image segmentation models require both high accuracy and lightweight design to accommodate real-world medical applications.<n>Existing pruning methods for model compression mostly overlook the intrinsic connections and similarity between the internal structures of complex deep neural networks.<n>We propose a hierarchical clustering compression method for medical image segmentation models (MIS-HCC)
  arXiv  Detail & Related papers  (2026-07-19T16:39:48Z)
• Fast Tensorization of Neural Networks via Slice-wise Feature Distillation [0.0]
  We propose a scalable tensorization framework for neural network compression based on slice-wise feature distillation.<n>We show significant gains over conventional global tensorization, achieving near-lossless compression at moderate compression rates.<n>Results on GPT-2 XL further demonstrate the scalability of the method and its applicability to large-scale models.
  arXiv  Detail & Related papers  (2026-05-19T13:37:53Z)
• Latent Sculpting for Zero-Shot Generalization: A Manifold Learning Approach to Out-of-Distribution Anomaly Detection [2.8547732086436306]
  A fundamental limitation of supervised deep learning is "Generalization Collapse"<n>We propose Latent Sculpting, a hierarchical two-stage representation learning framework.<n>We report an 88.89% detection rate on "Infiltration" scenarios.
  arXiv  Detail & Related papers  (2025-12-19T11:37:02Z)
• Rethinking Autoregressive Models for Lossless Image Compression via Hierarchical Parallelism and Progressive Adaptation [75.58269386927076]
  Autoregressive (AR) models are often dismissed as impractical due to prohibitive computational cost.<n>This work re-thinks this paradigm, introducing a framework built on hierarchical parallelism and progressive adaptation.<n> Experiments on diverse datasets (natural, satellite, medical) validate that our method achieves new state-of-the-art compression.
  arXiv  Detail & Related papers  (2025-11-14T06:27:58Z)
• Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compression [14.086434595924716]
  Mixture-of-Experts (MoE) Large Language Models (LLMs) face a trilemma of load imbalance, parameter redundancy, and communication overhead.<n>We introduce a unified framework based on dynamic expert clustering and structured compression to address these issues cohesively.
  arXiv  Detail & Related papers  (2025-09-27T10:45:58Z)
• Structure-Aware Automatic Channel Pruning by Searching with Graph Embedding [28.03880549472142]
  Channel pruning is a powerful technique to reduce the computational overhead of deep neural networks.<n>We propose a novel structure-aware automatic channel pruning (SACP) framework to model the network topology and learn the global importance of each channel.<n>SACP outperforms state-of-the-art pruning methods on compression efficiency and competitive on accuracy retention.
  arXiv  Detail & Related papers  (2025-06-13T05:05:35Z)
• Scalable Context-Preserving Model-Aware Deep Clustering for Hyperspectral Images [51.95768218975529]
  Subspace clustering has become widely adopted for the unsupervised analysis of hyperspectral images (HSIs)<n>Recent model-aware deep subspace clustering methods often use a two-stage framework, involving the calculation of a self-representation matrix with complexity of O(n2), followed by spectral clustering.<n>We propose a scalable, context-preserving deep clustering method based on basis representation, which jointly captures local and non-local structures for efficient HSI clustering.
  arXiv  Detail & Related papers  (2025-06-12T16:43:09Z)
• Quantize Once, Train Fast: Allreduce-Compatible Compression with Provable Guarantees [53.950234267704]
  We introduce Global-QSGD, an All-reduce gradient-compatible quantization method.<n>We show that it accelerates distributed training by up to 3.51% over baseline quantization methods.
  arXiv  Detail & Related papers  (2023-05-29T21:32:15Z)
• Low-rank Tensor Decomposition for Compression of Convolutional Neural Networks Using Funnel Regularization [1.8579693774597708]
  We propose a model reduction method to compress the pre-trained networks using low-rank tensor decomposition. A new regularization method, called funnel function, is proposed to suppress the unimportant factors during the compression. For ResNet18 with ImageNet2012, our reduced model can reach more than twi times speed up in terms of GMAC with merely 0.7% Top-1 accuracy drop.
  arXiv  Detail & Related papers  (2021-12-07T13:41:51Z)
• Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition [62.41259783906452]
  We present a novel global compression framework for deep neural networks. It automatically analyzes each layer to identify the optimal per-layer compression ratio. Our results open up new avenues for future research into the global performance-size trade-offs of modern neural networks.
  arXiv  Detail & Related papers  (2021-07-23T20:01:30Z)
• Efficient Micro-Structured Weight Unification and Pruning for Neural Network Compression [56.83861738731913]
  Deep Neural Network (DNN) models are essential for practical applications, especially for resource limited devices. Previous unstructured or structured weight pruning methods can hardly truly accelerate inference. We propose a generalized weight unification framework at a hardware compatible micro-structured level to achieve high amount of compression and acceleration.
  arXiv  Detail & Related papers  (2021-06-15T17:22:59Z)
• Preserved central model for faster bidirectional compression in distributed settings [12.323007278097249]
  We develop a new approach to tackle communication constraints in a distributed learning problem with a central server. We propose and analyze a new algorithm that performs bidirectional compression and achieves the same convergence rate as algorithms using only uplink (from the local workers to the central server) compression.
  arXiv  Detail & Related papers  (2021-02-24T19:48:20Z)
• Adaptive feature recombination and recalibration for semantic segmentation with Fully Convolutional Networks [57.64866581615309]
  We propose recombination of features and a spatially adaptive recalibration block that is adapted for semantic segmentation with Fully Convolutional Networks. Results indicate that Recombination and Recalibration improve the results of a competitive baseline, and generalize across three different problems.
  arXiv  Detail & Related papers  (2020-06-19T15:45:03Z)

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.