mlsanityData to 7 Oct 2026

Class-level Structural Relation Modelling and Smoothing for Visual Representation Learning

arXiv 2308.04142 ↗First posted 8 Aug 2023cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Representation learning for images has been advanced by recent progress in more complex neural models such as the Vision Transformers and new learning theories such as the structural causal models. However, these models mainly rely on the classification loss to implicitly regularize the class-level data distributions, and they may face difficulties when handling classes with diverse visual patterns. We argue that the incorporation of the structural information between data samples may improve this situation. To achieve this goal, this paper presents a framework termed Class-level Structural Relation Modeling and Smoothing for Visual Representation Learning (CSRMS), which includes the Class-level Relation Modelling, Class-aware Graph Sampling, and Relational Graph-Guided Representation Learning modules to model a relational graph of the entire dataset and perform class-aware smoothing and regularization operations to alleviate the issue of intra-class visual diversity and inter-class similarity. Specifically, the Class-level Relation Modelling module uses a clustering algorithm to learn the data distributions in the feature space and identify three types of class-level sample relations for the training set; Class-aware Graph Sampling module extends typical training batch construction process with three strategies to sample dataset-level sub-graphs; and Relational Graph-Guided Representation Learning module employs a graph convolution network with knowledge-guided smoothing operations to ease the projection from different visual patterns to the same class. Experiments demonstrate the effectiveness of structured knowledge modelling for enhanced representation learning and show that CSRMS can be incorporated with any state-of-the-art visual representation learning models for performance gains. The source codes and demos have been released at https://github.com/czt117/CSRMS.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 30 of its 61 references that are in the map. First posted on arXiv 8 Aug 2023.

Builds on

30 of 61 references.

References · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2017Graph Attention Networkscited by 8,854
  5. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  7. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  8. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  9. 2017Random Erasing Data Augmentationcited by 1,235
  10. 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 595
  11. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  12. 2018Generalizing Across Domains via Cross-Gradient Trainingcited by 268
18 more
  1. 2019Cross Attention Network for Few-shot Classificationcited by 218
  2. 2022Balanced Contrastive Learning for Long-Tailed Visual Recognitioncited by 143
  3. 2020Visual Compositional Learning for Human-Object Interaction Detectioncited by 129
  4. 2021Deconfounded Video Moment Retrieval with Causal Interventioncited by 84
  5. 2023Curricular Contrastive Regularization for Physics-aware Single Image Dehazingcited by 83
  6. 2020Embedding Propagation: Smoother Manifold for Few-Shot Classificationcited by 79
  7. 2021On the Integration of Self-Attention and Convolutioncited by 74
  8. 2020Tree-Augmented Cross-Modal Encoding for Complex-Query Video Retrievalcited by 47
  9. 2021Learning to Resize Images for Computer Vision Taskscited by 45
  10. 2023CUDA: Curriculum of Data Augmentation for Long-Tailed Recognitioncited by 30
  11. 2022BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learningcited by 29
  12. 2022Constructing Balance from Imbalance for Long-tailed Image Recognitioncited by 25
  13. 2022ProCo: Prototype-aware Contrastive Learning for Long-tailed Medical Image Classificationcited by 25
  14. 2023Triple Sequence Learning for Cross-domain Recommendationcited by 19
  15. 2023Incomplete Multi-View Multi-Label Learning via Label-Guided Masked View- and Category-Aware Transformerscited by 17
  16. 2022Meta-Causal Feature Learning for Out-of-Distribution Generalizationcited by 14
  17. 2023Cross-Modal Content Inference and Feature Enrichment for Cold-Start Recommendationcited by 5
  18. 2020Affinity Graph Supervision for Visual Recognitioncited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 6; 2026: 1.

9 papers.

  1. 2025Mamba as a Bridge: Where Vision Foundation Models Meet Vision Language Models for Domain-Generalized Semantic Segmentationcited by 23
  2. 2025Class-wise Balancing Data Replay for Federated Class-Incremental Learningcited by 9
  3. 20253DOT: Texture Transfer for 3DGS Objects from a Single Reference Imagecited by 7
  4. 2025GSAlign: Geometric and Semantic Alignment Network for Aerial-Ground Person Re-Identificationcited by 5
  5. 2025Global Intervention and Distillation for Federated Out-of-Distribution Generalizationcited by 3
  6. 2025ProtoConNet: Prototypical Augmentation and Alignment for Open-Set Few-Shot Image Classificationcited by 3
  7. 2024Unifying Visual and Semantic Feature Spaces with Diffusion Models for Enhanced Cross-Modal Alignmentcited by 1
  8. 2024Comparative Study of Neighbor-based Methods for Local Outlier Detectioncited by 0
  9. 2026From Selection to Scheduling: Federated Geometry-Aware Correction Makes Exemplar Replay Work Better under Continual Dynamic Heterogeneitycited by 0