CoChat
Sign Up
Cited by 1,274Advanced Neural Network ApplicationsVisual Attention and Saliency DetectionDomain Adaptation and Few-Shot Learning

The DOI matches its Crossref record; 52 of the 53 references it cites were found in a registry or an index.

Attentional Feature Fusion

Open access
Dai, Yimian, Gieseke, Fabian, Oehmcke, Stefan, Wu, Yiquan, Barnard, Kobus·2021·2021 IEEE Winter Conference on Applications of Computer Vision (WACV)
DOI 10.1109/wacv48630.2021.00360
Open this paper in CoChat — free accountOpen PDF

Abstract

Feature fusion, the combination of features from different layers or branches, is an omnipresent part of modern network architectures. It is often implemented via simple operations, such as summation or concatenation, but this might not be the best choice. In this work, we propose a uniform and general scheme, namely attentional feature fusion, which is applicable for most common scenarios, including feature fusion induced by short and long skip connections as well as within Inception layers. To better fuse features of inconsistent semantics and scales, we propose a multiscale channel attention module, which addresses issues that arise when fusing features given at different scales. We also demonstrate that the initial integration of feature maps can become a bottleneck and that this issue can be alleviated by adding another level of attention, which we refer to as iterative attentional feature fusion. With fewer layers or parameters, our models outperform state-of-the-art networks on both CIFAR-100 and ImageNet datasets, which suggests that more sophisticated attention mechanisms for feature fusion hold great potential to consistently yield better results compared to their direct counterparts. Our codes and trained models are available online1.

Overview

Integrity signals

Registry

Crossref · 10.1109/wacv48630.2021.00360

Cites

52 of 52 references verified0 citation errors · 0 not checkable

Statistics

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

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Citations

Cites

Show all 53 references

Research works printed but not linked: 1

  1. zhang, 2017, S3FD: Single shot scale-invariant face detector, 2017 IEEE International Conference on Computer Vision (ICCV)

Cited by

Sorted by citations

Items 601–700 of 1,000

Related

See all

Metadata

Authors
Dai, Y., Gieseke, F., Oehmcke, S., Wu, Y., & Barnard, K.
Affiliations
  • Nanjing University of Aeronautics and Astronautics (CN)
  • University of Copenhagen (DK)
  • University of Arizona (US)
ORCID
Venue
2021 IEEE Winter Conference on Applications of Computer Vision (WACV)
Publisher
IEEE
Published
2021-01
Pages
3559-3568
ISSN
2472-6737 (ISSN-L)
DOI
10.1109/wacv48630.2021.00360
OpenAlex
W3094897602
Semantic Scholar
33667aea67898e114ca100ee3e2b2a613b8a943a
Cited by
1,274
References
53
Citations by year
2026: 142 · 2025: 358 · 2024: 386 · 2023: 231 · 2022: 120 · 2021: 37
FWCI
63.17
Type
conference paper
Language
en
Open access
Licence
Locations
  • IEEE Winter Conference on Applications of Computer Vision (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • Research at the University of Copenhagen (University of Copenhagen) (submittedVersion)
  • arXiv (Cornell University)
Funders
  • National Natural Science Foundation of China
  • National Laboratory of Pattern Recognition
  • Nanjing University of Aeronautics and Astronautics
  • China Association for Science and Technology
  • China Scholarship Council
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
Keywords
attentional feature fusion, skip connections, attention mechanism, feature fusion

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