mlsanityData to 13 Oct 2026

Item Region-based Style Classification Network (IRSN): A Fashion Style Classifier Based on Domain Knowledge of Fashion Experts

arXiv 2512.20088 ↗First posted 23 Dec 2025cs.CV cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Fashion style classification is a challenging task because of the large visual variation within the same style and the existence of visually similar styles. Styles are expressed not only by the global appearance, but also by the attributes of individual items and their combinations. In this study, we propose an item region-based fashion style classification network (IRSN) to effectively classify fashion styles by analyzing item-specific features and their combinations in addition to global features. IRSN extracts features of each item region using item region pooling (IRP), analyzes them separately, and combines them using gated feature fusion (GFF). In addition, we improve the feature extractor by applying a dual-backbone architecture that combines a domain-specific feature extractor and a general feature extractor pre-trained with a large-scale image-text dataset. In experiments, applying IRSN to six widely-used backbones, including EfficientNet, ConvNeXt, and Swin Transformer, improved style classification accuracy by an average of 6.9% and a maximum of 14.5% on the FashionStyle14 dataset and by an average of 7.6% and a maximum of 15.1% on the ShowniqV3 dataset. Visualization analysis also supports that the IRSN models are better than the baseline models at capturing differences between similar style classes.

Key facts. Cited by 1 paper in the map (data through 13 Oct 2026). Builds on 36 of its 61 references that are in the map. First posted on arXiv 23 Dec 2025.

Builds on

36 of 61 references.

References · 36

  1. 2017Attention Is All You Needcited by 60,106
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,950
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,588
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,043
  5. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,321
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,111
  7. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,364
  8. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,713
  9. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,426
  10. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,457
  11. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,840
  12. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,786
24 more
  1. 2020Training data-efficient image transformers & distillation through attentioncited by 4,574
  2. 2014Going Deeper with Convolutionscited by 4,239
  3. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,836
  4. 2022A ConvNet for the 2020scited by 3,563
  5. 2015SSD: Single Shot MultiBox Detectorcited by 3,128
  6. 2015Fast R-CNNcited by 2,933
  7. 2018CBAM: Convolutional Block Attention Modulecited by 2,469
  8. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,418
  9. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,219
  10. 2021SimMIM: A Simple Framework for Masked Image Modelingcited by 1,150
  11. 2018CCNet: Criss-Cross Attention for Semantic Segmentationcited by 718
  12. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 705
  13. 2020Contrastive Learning of Medical Visual Representations from Paired Images and Textcited by 639
  14. 2021CoAtNet: Marrying Convolution and Attention for All Data Sizescited by 569
  15. 2021Image Segmentation Using Text and Image Promptscited by 511
  16. 2018Rethinking ImageNet Pre-trainingcited by 377
  17. 2019Using Pre-Training Can Improve Model Robustness and Uncertaintycited by 373
  18. 2019Axial Attention in Multidimensional Transformerscited by 356
  19. 2022How Do Vision Transformers Work?cited by 306
  20. 2021Focal Self-attention for Local-Global Interactions in Vision Transformerscited by 287
  21. 2015Learning Visual Features from Large Weakly Supervised Datacited by 165
  22. 2016Learning Visual N-Grams from Web Datacited by 95
  23. 2021CheXtransfer: Performance and Parameter Efficiency of ImageNet Models for Chest X-Ray Interpretationcited by 57
  24. 2019CC-Net: Image Complexity Guided Network Compression for Biomedical Image Segmentationcited by 13

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Holi-DETR: Holistic Fashion Item Detection Leveraging Contextual Informationcited by 0