Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 1,516

The DOI matches its Crossref record; 20 of the 20 references it cites were found in a registry or an index.

Deep Layer Aggregation

Open access
Yu, Fisher, Wang, Dequan, Shelhamer, Evan, Darrell, Trevor·2018·2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
DOI 10.1109/cvpr.2018.00255
Open this paper in CoChat — free account

Abstract

Visual recognition requires rich representations that span levels from low to high, scales from small to large, and resolutions from fine to coarse. Even with the depth of features in a convolutional network, a layer in isolation is not enough: compounding and aggregating these representations improves inference of what and where. Architectural efforts are exploring many dimensions for network backbones, designing deeper or wider architectures, but how to best aggregate layers and blocks across a network deserves further attention. Although skip connections have been incorporated to combine layers, these connections have been "shallow" themselves, and only fuse by simple, one-step operations. We augment standard architectures with deeper aggregation to better fuse information across layers. Our deep layer aggregation structures iteratively and hierarchically merge the feature hierarchy to make networks with better accuracy and fewer parameters. Experiments across architectures and tasks show that deep layer aggregation improves recognition and resolution compared to existing branching and merging schemes.

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.2018.00255

Cites

20 of 20 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 20 references

Research works printed but not linked: 31

  1. 10.1109/CVPR.2015.7298594 · DOI · Paper page
  2. srivastava, 2015, Highway networks, NIPS
  3. 10.1109/WACV.2017.16 · DOI
  4. maji, 2013, Fine-grained visual classification of aircraft
  5. simonyan, 2015, Very deep convolutional networks for large-scale image recognition, ICLRE
  6. shen, 2015, DeepContour: A deep convolutional feature learned by positive-sharing loss for contour detection, CVPR
  7. shelhamer, 2016, Fully convolutional networks for semantic segmentation, TPAMI
  8. lee, 2015, Deeply-supervised nets, Artificial Intelligence and Statistics, 562
  9. lin, 2014, Network in network, ICLRE
  10. 10.1109/TPAMI.2010.161 · DOI · Paper page
  11. iandola, 2016, Squeezenet Alexnet-level accuracy with 50x fewer parameters and< 0 5 mb model size
  12. 10.1109/ICCVW.2013.77 · DOI · Paper page
  13. kokkinos, 2016, Ubernet Training auniversal'convolutional neural network for low- mid- and high-level vision using diverse datasets and limited memory
  14. 10.1109/CVPR.2016.345 · DOI · Paper page
  15. larsson, 2017, Fractal-net: Ultra-deep neural networks without residuals, ICLRE
  16. 10.1109/ICCV.2013.231 · DOI · Paper page
  17. wah, 2011, The caltech-ucsd birds-200–2011 dataset
  18. 10.1109/CVPR.2016.41 · DOI · Paper page
  19. girshick, 2015, Region-based convolutional networks for accurate object detection and segmentation, TPAMI
  20. howard, 2013, Some Improvements on Deep Convolution Neural Network based Image Classification
  21. bishop, 2006, Pattern Recognition and Machine Learning, 229
  22. 10.1109/CVPR.2015.7299067 · DOI · Paper page
  23. 10.1016/j.patrec.2008.04.005 · DOI · Paper page
  24. bossard, 2014, Food-10 1-mining discriminative components with random forests, ECCV
  25. zhao, 2016, Pyramid Scene Parsing Network
  26. 10.1109/CVPR.2017.325 · DOI · Paper page
  27. 10.1109/CVPR.2017.75 · DOI · Paper page
  28. zeiler, 2014, Visualizing and understanding convolutional networks, ECCV
  29. 10.1109/ICCV.2015.164 · DOI · Paper page
  30. 10.1109/CVPR.2017.634 · DOI · Paper page
  31. 10.1109/CVPR.2016.28 · DOI · Paper page

Cited by

Metadata

Authors
Yu, F., Wang, D., Shelhamer, E., & Darrell, T.
Venue
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Publisher
IEEE
Published
2018-06
Pages
2403-2412
ISSN
1063-6919 (ISSN-L)
DOI
10.1109/cvpr.2018.00255
OpenAlex
W2963323244
Cited by
1,516
References
20
FWCI
44.23
Type
conference paper
Language
en
Open access
green

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.