mlsanityData to 14 Oct 2026

Semantic Feature Integration network for Fine-grained Visual Classification

arXiv 2302.10275 ↗First posted 13 Feb 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Fine-Grained Visual Classification (FGVC) is known as a challenging task due to subtle differences among subordinate categories. Many current FGVC approaches focus on identifying and locating discriminative regions by using the attention mechanism, but neglect the presence of unnecessary features that hinder the understanding of object structure. These unnecessary features, including 1) ambiguous parts resulting from the visual similarity in object appearances and 2) noninformative parts (e.g., background noise), can have a significant adverse impact on classification results. In this paper, we propose the Semantic Feature Integration network (SFI-Net) to address the above difficulties. By eliminating unnecessary features and reconstructing the semantic relations among discriminative features, our SFI-Net has achieved satisfying performance. The network consists of two modules: 1) the multi-level feature filter (MFF) module is proposed to remove unnecessary features with different receptive field, and then concatenate the preserved features on pixel level for subsequent disposal; 2) the semantic information reconstitution (SIR) module is presented to further establish semantic relations among discriminative features obtained from the MFF module. These two modules are carefully designed to be light-weighted and can be trained end-to-end in a weakly-supervised way. Extensive experiments on four challenging fine-grained benchmarks demonstrate that our proposed SFI-Net achieves the state-of-the-arts performance. Especially, the classification accuracy of our model on CUB-200-2011 and Stanford Dogs reaches 92.64% and 93.03%, respectively.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 31 of its 44 references that are in the map. First posted on arXiv 13 Feb 2023.

Builds on

31 of 44 references.

References · 31

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  5. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  6. 2013Fine-Grained Visual Classification of Aircraftcited by 1,726
  7. 2015Bilinear CNNs for Fine-grained Visual Recognitioncited by 228
  8. 2018Adversarial Complementary Learning for Weakly Supervised Object Localizationcited by 166
  9. 2021TransFG: A Transformer Architecture for Fine-grained Recognitioncited by 132
  10. 2021Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identificationcited by 114
  11. 2014Part-based R-CNNs for Fine-grained Category Detectioncited by 109
  12. 2020Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patchescited by 92
19 more
  1. 2020Learning Attentive Pairwise Interaction for Fine-Grained Classificationcited by 84
  2. 2022Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identificationcited by 78
  3. 2015Part-Stacked CNN for Fine-Grained Visual Categorizationcited by 62
  4. 2020Talking-Heads Attentioncited by 62
  5. 2020SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Datacited by 56
  6. 2014Bird Species Categorization Using Pose Normalized Deep Convolutional Netscited by 50
  7. 2021Feature Fusion Vision Transformer for Fine-Grained Visual Categorizationcited by 40
  8. 2021RAMS-Trans: Recurrent Attention Multi-scale Transformer forFine-grained Image Recognitioncited by 34
  9. 2021Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classificationcited by 31
  10. 2022SR-GNN: Spatial Relation-aware Graph Neural Network for Fine-Grained Image Categorizationcited by 21
  11. 2020Look-into-Object: Self-supervised Structure Modeling for Object Recognitioncited by 20
  12. 2022SIM-Trans: Structure Information Modeling Transformer for Fine-grained Visual Categorizationcited by 19
  13. 2021A free lunch from ViT:Adaptive Attention Multi-scale Fusion Transformer for Fine-grained Visual Recognitioncited by 16
  14. 2020Attribute Mix: Semantic Data Augmentation for Fine Grained Recognitioncited by 15
  15. 2020Learning Semantically Enhanced Feature for Fine-Grained Image Classificationcited by 12
  16. 2022A Novel Plug-in Module for Fine-Grained Visual Classificationcited by 11
  17. 2016Mask-CNN: Localizing Parts and Selecting Descriptors for Fine-Grained Image Recognitioncited by 10
  18. 2022Fine-Grained Visual Classification using Self Assessment Classifiercited by 8
  19. 2019ELoPE: Fine-Grained Visual Classification with Efficient Localization, Pooling and Embeddingcited by 7

Built on by

Not cited yet.