mlsanityData to 7 Oct 2026

From BoW to CNN: Two Decades of Texture Representation for Texture Classification

arXiv 1801.10324 ↗First posted 31 Jan 2018cs.CV cs.LGcited by 39

Not on the map. Why?

Abstract (arXiv)

Texture is a fundamental characteristic of many types of images, and texture representation is one of the essential and challenging problems in computer vision and pattern recognition which has attracted extensive research attention. Since 2000, texture representations based on Bag of Words (BoW) and on Convolutional Neural Networks (CNNs) have been extensively studied with impressive performance. Given this period of remarkable evolution, this paper aims to present a comprehensive survey of advances in texture representation over the last two decades. More than 200 major publications are cited in this survey covering different aspects of the research, which includes (i) problem description; (ii) recent advances in the broad categories of BoW-based, CNN-based and attribute-based methods; and (iii) evaluation issues, specifically benchmark datasets and state of the art results. In retrospect of what has been achieved so far, the survey discusses open challenges and directions for future research.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). First posted on arXiv 31 Jan 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 9; 2022: 9; 2023: 8; 2024: 5; 2025: 4; 2026: 3.

39 papers.

Sort:

By area:

  1. 2021Pixel Difference Networks for Efficient Edge Detectioncited by 167
  2. 2021Deep Texture-Aware Features for Camouflaged Object Detectioncited by 36
  3. 2022Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Poolingcited by 19
  4. 2024Lightweight Pixel Difference Networks for Efficient Visual Representation Learningcited by 17
  5. 2021Semantic Distribution-aware Contrastive Adaptation for Semantic Segmentationcited by 14
  6. 2021Deep Face Fuzzy Vault: Implementation and Performancecited by 12
  7. 2023RADAM: Texture Recognition through Randomized Aggregated Encoding of Deep Activation Mapscited by 12
  8. 2021Deep Learning for Scene Classification: A Surveycited by 9
  9. 2023Discovering and Explaining the Non-Causality of Deep Learning in SAR ATRcited by 9
  10. 2022Attentional Feature Refinement and Alignment Network for Aircraft Detection in SAR Imagerycited by 7
  11. 2023Hierarchical Disentanglement-Alignment Network for Robust SAR Vehicle Recognitioncited by 6
  12. 2024A Comparative Survey of Vision Transformers for Feature Extraction in Texture Analysiscited by 6
27 more
  1. 2023A Study on the Generality of Neural Network Structures for Monocular Depth Estimationcited by 4
  2. 2021Explainable Systematic Analysis for Synthetic Aperture Sonar Imagerycited by 3
  3. 2022Median Pixel Difference Convolutional Network for Robust Face Recognitioncited by 3
  4. 2022Texture Representation via Analysis and Synthesis with Generative Adversarial Networkscited by 3
  5. 2025Hierarchical Material Recognition from Local Appearancecited by 3
  6. 2021A Novel Bio-Inspired Texture Descriptor based on Biodiversity and Taxonomic Measurescited by 2
  7. 2021Efficient Visual Recognition with Deep Neural Networks: A Survey on Recent Advances and New Directionscited by 2
  8. 2022Automatic extraction of coronary arteries using deep learning in invasive coronary angiogramscited by 2
  9. 2022Histogram Layers for Synthetic Aperture Sonar Imagerycited by 2
  10. 2024Histogram Layers for Neural Engineered Featurescited by 2
  11. 2024PDCFNet: Enhancing Underwater Images through Pixel Difference Convolutioncited by 2
  12. 2026Perceptual misalignment of texture representations in convolutional neural networkscited by 2
  13. 2020Texture image classification based on a pseudo-parabolic diffusion modelcited by 1
  14. 2021Image Classifiers for Network Intrusionscited by 1
  15. 2023Deep Learning in the Field of Biometric Template Protection: An Overviewcited by 1
  16. 2023Improved Benthic Classification using Resolution Scaling and SymmNet Unsupervised Domain Adaptationcited by 1
  17. 2025VORTEX: Challenging CNNs at Texture Recognition by using Vision Transformers with Orderless and Randomized Token Encodingscited by 1
  18. 2022Multiscale Analysis for Improving Texture Classificationcited by 0
  19. 2022Texture Extraction Methods Based Ensembling Framework for Improved Classificationcited by 0
  20. 2022A patch-based architecture for multi-label classification from single label annotationscited by 0
  21. 2023Comparing PSDNet, pretrained networks, and traditional feature extraction for predicting the particle size distribution of granular materials from photographscited by 0
  22. 2023Multimodal Multi-User Surface Recognition with the Kernel Two-Sample Testcited by 0
  23. 2024Empirical curvelet based Fully Convolutional Network for supervised texture image segmentationcited by 0
  24. 2025GraphTEN: Graph Enhanced Texture Encoding Networkcited by 0
  25. 2025MIXER: Mixed Hyperspherical Random Embedding Neural Network for Texture Recognitioncited by 0
  26. 2026Where Does Texture Evidence Live in SAM? Features, Proposal Masks, and Texture Segmentationcited by 0
  27. 2026Texture Image Classification Using DWT AlexNet Feature Fusion and Deep Neural Networkscited by 0