Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 1,400

The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.

Look Closer to See Better: Recurrent Attention Convolutional Neural Network for Fine-Grained Image Recognition

Fu, Jianlong, Zheng, Heliang, Mei, Tao·2017·2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
DOI 10.1109/cvpr.2017.476
Open this paper in CoChat — free account

Abstract

Recognizing fine-grained categories (e.g., bird species) is difficult due to the challenges of discriminative region localization and fine-grained feature learning. Existing approaches predominantly solve these challenges independently, while neglecting the fact that region detection and fine-grained feature learning are mutually correlated and thus can reinforce each other. In this paper, we propose a novel recurrent attention convolutional neural network (RA-CNN) which recursively learns discriminative region attention and region-based feature representation at multiple scales in a mutual reinforced way. The learning at each scale consists of a classification sub-network and an attention proposal sub-network (APN). The APN starts from full images, and iteratively generates region attention from coarse to fine by taking previous prediction as a reference, while the finer scale network takes as input an amplified attended region from previous scale in a recurrent way. The proposed RA-CNN is optimized by an intra-scale classification loss and an inter-scale ranking loss, to mutually learn accurate region attention and fine-grained representation. RA-CNN does not need bounding box/part annotations and can be trained end-to-end. We conduct comprehensive experiments and show that RA-CNN achieves the best performance in three fine-grained tasks, with relative accuracy gains of 3.3%, 3.7%, 3.8%, on CUB Birds, Stanford Dogs and Stanford Cars, respectively.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/cvpr.2017.476

Cites

5 of 5 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 5 references

Research works printed but not linked: 30

  1. zhang, 2014, Part-based R-CNNs for fine-grained category detection, ECCV, 1173
  2. 10.1109/CVPR.2016.129 · DOI · Paper page
  3. xiao, 2015, The application of two-level attention models in deep convolutional neural network for fine-grained image classification, CVPR, 842
  4. welinder, 2010, Caltech-UCSD Birds 200, Technical Report CNS-TR-2010-001
  5. zhao, 2016, Diversified visual attention networks for fine-grained object classification
  6. 10.1109/CVPR.2016.128 · DOI · Paper page
  7. huang, 2016, Part-stacked CNN for fine-grained visual categorization, CVPR, 1173
  8. jaderberg, 2015, Spatial transformer networks, NIPS, 2017
  9. 10.1109/CVPR.2016.494 · DOI · Paper page
  10. khosla, 2011, Novel dataset for fine-grained image categorization, ICCV Workshop
  11. 10.1109/CVPR.2015.7299194 · DOI · Paper page
  12. krause, 2016, The unreasonable effectiveness of noisy data for fine-grained recognition, ECCV, 301
  13. 10.1109/ICCVW.2013.77 · DOI · Paper page
  14. 10.1109/CVPR.2015.7298775 · DOI · Paper page
  15. 10.1109/ICCV.2015.170 · DOI · Paper page
  16. 10.1109/ICCV.2015.276 · DOI · Paper page
  17. 10.1145/2736277.2741112 · DOI
  18. simonyan, 2015, Very deep convolutional networks for large-scale image recognition, ICLRE, 1409
  19. 10.1109/ICCV.2015.230 · DOI
  20. wang, 2016, Beyond object recognition: Visual sentiment analysis with deep coupled adjective and noun neural networks, IJCAI
  21. 10.1109/TCSVT.2014.2380211 · DOI
  22. 10.1109/CVPR.2014.81 · DOI · Paper page
  23. branson, 2014, Bird species categorization using pose normalized deep convolutional nets, BMVC
  24. anne, 2016, Deep compositional captioning: Describing novel object categories without paired training data, CVPR
  25. liu, 2016, Fully convolutional attention localization networks Efficient attention localization for fine-grained recognition
  26. 10.1109/ICCV.2011.6126398 · DOI
  27. 10.1109/CVPR.2006.42 · DOI · Paper page
  28. 10.1109/CVPR.2016.13 · DOI · Paper page
  29. 10.1109/CVPR.2015.7298998 · DOI
  30. 10.1109/ICCV.2015.136 · DOI · Paper page

Cited by

Metadata

Authors
Fu, J., Zheng, H., & Mei, T.
Venue
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2017-07
Pages
4476-4484
ISSN
1063-6919 (ISSN-L)
DOI
10.1109/cvpr.2017.476
OpenAlex
W2737725206
Cited by
1,400
References
5
FWCI
39.07
Type
conference paper
Language
en
Open access
closed

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.