MSPCaps: A Multi-Scale Patchify Capsule Network with Cross-Agreement Routing for Visual Recognition

• URL: http://arxiv.org/abs/2508.16922v1
• Date: Sat, 23 Aug 2025 06:56:00 GMT
• Title: MSPCaps: A Multi-Scale Patchify Capsule Network with Cross-Agreement Routing for Visual Recognition
• Authors: Yudong Hu, Yueju Han, Rui Sun, Jinke Ren,
• Abstract summary: We propose the Multi-Scale Patchify Capsule Network (MSPCaps), a novel architecture that integrates multi-scale feature learning and efficient capsule routing.<n>Our proposed MSPCaps achieves remarkable scalability and superior robustness, consistently surpassing multiple baseline methods in terms of classification accuracy.
• Score: 9.549109171438394
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Capsule Network (CapsNet) has demonstrated significant potential in visual recognition by capturing spatial relationships and part-whole hierarchies for learning equivariant feature representations. However, existing CapsNet and variants often rely on a single high-level feature map, overlooking the rich complementary information from multi-scale features. Furthermore, conventional feature fusion strategies (e.g., addition and concatenation) struggle to reconcile multi-scale feature discrepancies, leading to suboptimal classification performance. To address these limitations, we propose the Multi-Scale Patchify Capsule Network (MSPCaps), a novel architecture that integrates multi-scale feature learning and efficient capsule routing. Specifically, MSPCaps consists of three key components: a Multi-Scale ResNet Backbone (MSRB), a Patchify Capsule Layer (PatchifyCaps), and Cross-Agreement Routing (CAR) blocks. First, the MSRB extracts diverse multi-scale feature representations from input images, preserving both fine-grained details and global contextual information. Second, the PatchifyCaps partitions these multi-scale features into primary capsules using a uniform patch size, equipping the model with the ability to learn from diverse receptive fields. Finally, the CAR block adaptively routes the multi-scale capsules by identifying cross-scale prediction pairs with maximum agreement. Unlike the simple concatenation of multiple self-routing blocks, CAR ensures that only the most coherent capsules contribute to the final voting. Our proposed MSPCaps achieves remarkable scalability and superior robustness, consistently surpassing multiple baseline methods in terms of classification accuracy, with configurations ranging from a highly efficient Tiny model (344.3K parameters) to a powerful Large model (10.9M parameters), highlighting its potential in advancing feature representation learning.

Related papers

• PFF-Net: Patch Feature Fitting for Point Cloud Normal Estimation [81.94096000733127]
  We present a new idea of feature extraction for robust normal estimation of point clouds.<n>We use the fusion of multi-scale features from different neighborhood sizes to address the issue of selecting reasonable patch sizes for various data or geometries.<n>Our approximation strategy based on aggregating the features of multiple scales enables the model to achieve scale adaptation of varying local patches.
  arXiv  Detail & Related papers  (2025-11-26T13:12:14Z)
• Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation [61.91492500828508]
  Few-shot 3D point cloud segmentation (FS-PCS) aims at generalizing models to segment novel categories with minimal support samples.<n>We introduce a multimodal FS-PCS setup, utilizing textual labels and the potentially available 2D image modality.<n>We propose a simple yet effective Test-time Adaptive Cross-modal (TACC) technique to mitigate training bias.
  arXiv  Detail & Related papers  (2024-10-29T19:28:41Z)
• Deep multi-prototype capsule networks [0.3823356975862005]
  Capsule networks are a type of neural network that identify image parts and form the instantiation parameters of a whole hierarchically. This paper presents a multi-prototype architecture for guiding capsule networks to represent the variations in the image parts. The experimental results on MNIST, SVHN, C-Cube, CEDAR, MCYT, and UTSig datasets reveal that the proposed model outperforms others regarding image classification accuracy.
  arXiv  Detail & Related papers  (2024-04-23T18:37:37Z)
• Dual-scale Enhanced and Cross-generative Consistency Learning for Semi-supervised Medical Image Segmentation [49.57907601086494]
  Medical image segmentation plays a crucial role in computer-aided diagnosis. We propose a novel Dual-scale Enhanced and Cross-generative consistency learning framework for semi-supervised medical image (DEC-Seg)
  arXiv  Detail & Related papers  (2023-12-26T12:56:31Z)
• Edge-aware Feature Aggregation Network for Polyp Segmentation [38.11584888416297]
  In this study, we present a novel Edge-aware Feature Aggregation Network (EFA-Net) for polyp segmentation.<n>EFA-Net can fully make use of cross-level and multi-scale features to enhance the performance of polyp segmentation.<n> Experimental results on five widely adopted colonoscopy datasets show that our EFA-Net outperforms state-of-the-art polyp segmentation methods in terms of generalization and effectiveness.
  arXiv  Detail & Related papers  (2023-09-19T11:09:38Z)
• PARFormer: Transformer-based Multi-Task Network for Pedestrian Attribute Recognition [23.814762073093153]
  We propose a pure transformer-based multi-task PAR network named PARFormer, which includes four modules. In the feature extraction module, we build a strong baseline for feature extraction, which achieves competitive results on several PAR benchmarks. In the viewpoint perception module, we explore the impact of viewpoints on pedestrian attributes, and propose a multi-view contrastive loss. In the attribute recognition module, we alleviate the negative-positive imbalance problem to generate the attribute predictions.
  arXiv  Detail & Related papers  (2023-04-14T16:27:56Z)
• Progressive Multi-scale Consistent Network for Multi-class Fundus Lesion Segmentation [28.58972084293778]
  We propose a progressive multi-scale consistent network (PMCNet) that integrates the proposed progressive feature fusion (PFF) block and dynamic attention block (DAB) PFF block progressively integrates multi-scale features from adjacent encoding layers, facilitating feature learning of each layer by aggregating fine-grained details and high-level semantics. DAB is designed to dynamically learn the attentive cues from the fused features at different scales, thus aiming to smooth the essential conflicts existing in multi-scale features.
  arXiv  Detail & Related papers  (2022-05-31T12:10:01Z)
• SAR Image Change Detection Based on Multiscale Capsule Network [33.524488071386415]
  Traditional synthetic aperture radar image change detection methods face the challenges of speckle noise and deformation sensitivity. We propose a Multiscale Capsule Network (Ms-CapsNet) to extract the discriminative information between the changed and unchanged pixels. The effectiveness of the proposed Ms-CapsNet is verified on three real SAR datasets.
  arXiv  Detail & Related papers  (2022-01-22T01:30:36Z)
• Multi-level Second-order Few-shot Learning [111.0648869396828]
  We propose a Multi-level Second-order (MlSo) few-shot learning network for supervised or unsupervised few-shot image classification and few-shot action recognition. We leverage so-called power-normalized second-order base learner streams combined with features that express multiple levels of visual abstraction. We demonstrate respectable results on standard datasets such as Omniglot, mini-ImageNet, tiered-ImageNet, Open MIC, fine-grained datasets such as CUB Birds, Stanford Dogs and Cars, and action recognition datasets such as HMDB51, UCF101, and mini-MIT.
  arXiv  Detail & Related papers  (2022-01-15T19:49:00Z)
• Specificity-preserving RGB-D Saliency Detection [103.3722116992476]
  We propose a specificity-preserving network (SP-Net) for RGB-D saliency detection. Two modality-specific networks and a shared learning network are adopted to generate individual and shared saliency maps. Experiments on six benchmark datasets demonstrate that our SP-Net outperforms other state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-08-18T14:14:22Z)
• Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformers [124.01928050651466]
  We propose a new type of polyp segmentation method, named Polyp-PVT. The proposed model, named Polyp-PVT, effectively suppresses noises in the features and significantly improves their expressive capabilities.
  arXiv  Detail & Related papers  (2021-08-16T07:09:06Z)
• Learning Deep Multimodal Feature Representation with Asymmetric Multi-layer Fusion [63.72912507445662]
  We propose a compact and effective framework to fuse multimodal features at multiple layers in a single network. We verify that multimodal features can be learnt within a shared single network by merely maintaining modality-specific batch normalization layers in the encoder. Secondly, we propose a bidirectional multi-layer fusion scheme, where multimodal features can be exploited progressively.
  arXiv  Detail & Related papers  (2021-08-11T03:42:13Z)

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.