mlsanityData to 7 Oct 2026

An attention-driven hierarchical multi-scale representation for visual recognition

arXiv 2110.12178 ↗First posted 23 Oct 2021cs.CV cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Convolutional Neural Networks (CNNs) have revolutionized the understanding of visual content. This is mainly due to their ability to break down an image into smaller pieces, extract multi-scale localized features and compose them to construct highly expressive representations for decision making. However, the convolution operation is unable to capture long-range dependencies such as arbitrary relations between pixels since it operates on a fixed-size window. Therefore, it may not be suitable for discriminating subtle changes (e.g. fine-grained visual recognition). To this end, our proposed method captures the high-level long-range dependencies by exploring Graph Convolutional Networks (GCNs), which aggregate information by establishing relationships among multi-scale hierarchical regions. These regions consist of smaller (closer look) to larger (far look), and the dependency between regions is modeled by an innovative attention-driven message propagation, guided by the graph structure to emphasize the neighborhoods of a given region. Our approach is simple yet extremely effective in solving both the fine-grained and generic visual classification problems. It outperforms the state-of-the-arts with a significant margin on three and is very competitive on other two datasets.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 54 of its 89 references that are in the map. First posted on arXiv 23 Oct 2021.

Builds on

54 of 89 references.

References · 54

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2017Graph Attention Networkscited by 8,854
  5. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  6. 2016Wide Residual Networkscited by 3,057
  7. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  8. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  9. 2017Non-local Neural Networkscited by 2,290
  10. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  11. 2013Fine-Grained Visual Classification of Aircraftcited by 1,701
  12. 2017Random Erasing Data Augmentationcited by 1,235
38 more
  1. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
  2. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,061
  3. 2021Transformers in Vision: A Surveycited by 1,009
  4. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 786
  5. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
  6. 2017Deep Mutual Learningcited by 621
  7. 2019Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillationcited by 491
  8. 2019Graph U-Netscited by 489
  9. 2019Self-Attention Graph Poolingcited by 421
  10. 2018Rethinking ImageNet Pre-trainingcited by 376
  11. 2018Explicit Inductive Bias for Transfer Learning with Convolutional Networkscited by 226
  12. 2019A Survey of the Recent Architectures of Deep Convolutional Neural Networkscited by 211
  13. 2019Local Relation Networks for Image Recognitioncited by 210
  14. 2018Learning Human-Object Interactions by Graph Parsing Neural Networkscited by 176
  15. 2018Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learningcited by 174
  16. 2020Regularizing Class-wise Predictions via Self-knowledge Distillationcited by 144
  17. 2019Relation-Aware Global Attention for Person Re-identificationcited by 124
  18. 2019Orthogonal Convolutional Neural Networkscited by 122
  19. 2019Relation-Aware Graph Attention Network for Visual Question Answeringcited by 119
  20. 2018Learning to Navigate for Fine-grained Classificationcited by 103
  21. 2019Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognitioncited by 95
  22. 2020Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patchescited by 92
  23. 2014The Application of Two-level Attention Models in Deep Convolutional Neural Network for Fine-grained Image Classificationcited by 67
  24. 2019Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification from the Bottom Upcited by 66
  25. 2020The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classificationcited by 64
  26. 2017Object-Part Attention Model for Fine-grained Image Classificationcited by 54
  27. 2017Borrowing Treasures from the Wealthy: Deep Transfer Learning through Selective Joint Fine-tuningcited by 48
  28. 2018Hierarchical Bilinear Pooling for Fine-Grained Visual Recognitioncited by 47
  29. 2018Deep Reasoning with Knowledge Graph for Social Relationship Understandingcited by 44
  30. 2019Deep Learning on Small Datasets without Pre-Training using Cosine Losscited by 41
  31. 2020Second-Order Pooling for Graph Neural Networkscited by 33
  32. 2021Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classificationcited by 31
  33. 2018Fine-Grained Representation Learning and Recognition by Exploiting Hierarchical Semantic Embeddingcited by 28
  34. 2015Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networkscited by 22
  35. 2019Pay attention to the activations: a modular attention mechanism for fine-grained image recognitioncited by 12
  36. 2021Re-rank Coarse Classification with Local Region Enhanced Features for Fine-Grained Image Recognitioncited by 11
  37. 2016InterActive: Inter-Layer Activeness Propagationcited by 6
  38. 2020Focus Longer to See Better:Recursively Refined Attention for Fine-Grained Image Classificationcited by 4

50 most cited of 54 All 54 (JSON)

Built on by

Not cited yet.