CoChat
Sign Up
Cited by 1,045Advanced Neural Network ApplicationsAdvanced Image and Video Retrieval TechniquesDomain Adaptation and Few-Shot Learning

The DOI matches its Crossref record; 37 of the 40 references it cites were found in a registry or an index.

Learning Multi-attention Convolutional Neural Network for Fine-Grained Image Recognition

Zheng, Heliang, Fu, Jianlong, Mei, Tao, Luo, Jiebo·2017·2017 IEEE International Conference on Computer Vision (ICCV)
DOI 10.1109/iccv.2017.557
Open this paper in CoChat — free account

Abstract

Recognizing fine-grained categories (e.g., bird species) highly relies on discriminative part localization and part-based fine-grained feature learning. Existing approaches predominantly solve these challenges independently, while neglecting the fact that part localization (e.g., head of a bird) and fine-grained feature learning (e.g., head shape) are mutually correlated. In this paper, we propose a novel part learning approach by a multi-attention convolutional neural network (MA-CNN), where part generation and feature learning can reinforce each other. MA-CNN consists of convolution, channel grouping and part classification sub-networks. The channel grouping network takes as input feature channels from convolutional layers, and generates multiple parts by clustering, weighting and pooling from spatially-correlated channels. The part classification network further classifies an image by each individual part, through which more discriminative fine-grained features can be learned. Two losses are proposed to guide the multi-task learning of channel grouping and part classification, which encourages MA-CNN to generate more discriminative parts from feature channels and learn better fine-grained features from parts in a mutual reinforced way. MA-CNN does not need bounding box/part annotation and can be trained end-to-end. We incorporate the learned parts from MA-CNN with part-CNN for recognition, and show the best performances on three challenging published fine-grained datasets, e.g., CUB-Birds, FGVC-Aircraft and Stanford-Cars.

Overview

Integrity signals

Registry

Crossref · 10.1109/iccv.2017.557

Cites

37 of 37 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Citations

Cites

Flagged first, then by citations

Show all 40 references

3 of the 40 references couldn’t be matched to a known paper.

Research works printed but not linked: 2

  1. welinder, 2010, Caltech-Ucsd Birds 200, Technical Report
  2. khosla, 2011, Novel dataset for fine-grained image categorization, ICCV Workshop

Cited by

Sorted by citations

Items 801–900 of 1,000

Related

See all

Metadata

Authors
Zheng, H., Fu, J., Mei, T., & Luo, J.
Affiliations
  • University of Science and Technology of China (CN)
  • Microsoft Research Asia (China) (CN)
  • University of Rochester (US)
ORCID
Venue
2017 IEEE International Conference on Computer Vision (ICCV)
Publisher
IEEE
Published
2017-10
Pages
5219-5227
DOI
10.1109/iccv.2017.557
OpenAlex
W2773003563
Cited by
1,045
References
40
Citations by year
2026: 33 · 2025: 71 · 2024: 126 · 2023: 153 · 2022: 143 · 2021: 206 · 2020: 145 · 2019: 111 · 2018: 56 · 2017: 1
FWCI
25.02
Type
conference paper
Language
en
Open access
closed
Locations
IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
Keywords
fine-grained image classification, part localization, channel grouping, part classification, multi-task learning, representation learning, end-to-end learning, bird identification, aircraft recognition, vehicle identification

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