Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 3,385

The DOI matches its Crossref record; 21 of the 21 references it cites were found in a registry or an index.

Res2Net: A New Multi-Scale Backbone Architecture

Open access
Gao, Shang-Hua, Cheng, Ming-Ming, Zhao, Kai, Zhang, Xin-Yu, Yang, Ming-Hsuan, Torr, Philip·2021·IEEE Transactions on Pattern Analysis and Machine Intelligence
DOI 10.1109/tpami.2019.2938758
Open this paper in CoChat — free account

Abstract

Representing features at multiple scales is of great importance for numerous vision tasks. Recent advances in backbone convolutional neural networks (CNNs) continually demonstrate stronger multi-scale representation ability, leading to consistent performance gains on a wide range of applications. However, most existing methods represent the multi-scale features in a layer-wise manner. In this paper, we propose a novel building block for CNNs, namely Res2Net, by constructing hierarchical residual-like connections within one single residual block. The Res2Net represents multi-scale features at a granular level and increases the range of receptive fields for each network layer. The proposed Res2Net block can be plugged into the state-of-the-art backbone CNN models, e.g., ResNet, ResNeXt, and DLA. We evaluate the Res2Net block on all these models and demonstrate consistent performance gains over baseline models on widely-used datasets, e.g., CIFAR-100 and ImageNet. Further ablation studies and experimental results on representative computer vision tasks, i.e., object detection, class activation mapping, and salient object detection, further verify the superiority of the Res2Net over the state-of-the-art baseline methods. The source code and trained models are available on https://mmcheng.net/res2net/.

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/tpami.2019.2938758

Cites

21 of 21 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 21 references

Research works printed but not linked: 50

  1. 10.1109/CVPR.2015.7298965 · DOI · Paper page
  2. lin, 2014, Microsoft COCO: Common objects in context, Proc Eur Conf Comput Vis, 740
  3. lin, 2013, Network in network, Proc Int Conf Learn Representations
  4. 10.1109/CVPR.2014.43 · DOI · Paper page
  5. 10.1109/TPAMI.2018.2878849 · DOI · Paper page
  6. liu, 2016, SSD: Single shot multibox detector, Proc Eur Conf Comput Vis, 21
  7. liu, 2011, Learning to detect a salient object, IEEE Trans Pattern Anal Mach Intell, 33, 353, 10.1109/TPAMI.2010.70 · DOI · Paper page
  8. 10.1109/CVPR.2019.00404 · DOI · Paper page
  9. 10.1109/CVPR.2018.00255 · DOI · Paper page
  10. 10.1109/ICCV.2017.31 · DOI · Paper page
  11. 10.1109/CVPR.2017.512 · DOI · Paper page
  12. 10.1109/CVPR.2017.660 · DOI · Paper page
  13. 10.1109/CVPR.2019.00405 · DOI · Paper page
  14. 10.1109/ICCV.2019.00894 · DOI
  15. li, 2015, Visual saliency based on multiscale deep features, Proc IEEE Conf Comput Vis Pattern Recognit, 5455
  16. 10.24963/ijcai.2018/166 · DOI
  17. 10.1109/CVPR.2015.7298731 · DOI · Paper page
  18. 10.1007/s41095-019-0149-9 · DOI · Paper page
  19. 10.1109/34.993558 · DOI · Paper page
  20. 10.1109/ICCV.2011.6126343 · DOI · Paper page
  21. 10.1109/TPAMI.2015.2389824 · DOI · Paper page
  22. 10.1109/ICCV.2017.322 · DOI · Paper page
  23. 10.1109/TPAMI.2018.2815688 · DOI · Paper page
  24. 10.1109/CVPR.2015.7298594 · DOI · Paper page
  25. 10.1109/CVPR.2013.407 · DOI · Paper page
  26. 10.1109/CVPR.2013.153 · DOI · Paper page
  27. 10.1109/ICCV.2015.164 · DOI · Paper page
  28. 10.1109/CVPR.2017.634 · DOI · Paper page
  29. xiao, 2018, Simple baselines for human pose estimation and tracking, Proc Eur Conf Comput Vis, 472
  30. 10.1109/CVPR.2017.687 · DOI · Paper page
  31. 10.1007/s11263-016-0977-3 · DOI
  32. chen, 2017, Dual path networks, Proc Int Conf Neural Inf Process, 4467
  33. cheng, 2019, High frequency residual learning for multi-scale image classification, Proc Brit Mach Vis Conf
  34. 10.1007/s41095-018-0120-1 · DOI
  35. 10.1109/TPAMI.2014.2345401 · DOI · Paper page
  36. cheng, 2017, A survey of model compression and acceleration for deep neural networks, CoRR arXiv 1710 09282
  37. 10.1109/CVPR.2014.81 · DOI · Paper page
  38. han, 2015, Learning both weights and connections for efficient neural network, Proc Int Conf Neural Inf Process, 1135
  39. 10.1109/ICCV.2017.116 · DOI · Paper page
  40. 10.1109/TIP.2015.2487833 · DOI · Paper page
  41. 10.1109/TPAMI.2017.2699184 · DOI · Paper page
  42. chen, 2019, Big-little net: An efficient multi-scale feature representation for visual and speech recognition, Proc Int Conf Learn Representations
  43. chen, 2017, Rethinking atrous convolution for semantic image segmentation, CoRR abs/1706 05587
  44. sun, 2019, High-resolution representations for labeling pixels and regions, CoRR abs/1904 04514
  45. 10.1109/ICCV.2019.00353 · DOI · Paper page
  46. simonyan, 2014, Two-stream convolutional networks for action recognition in videos, Proc Int Conf Neural Inf Process, 568
  47. 10.1109/CVPR.2019.00584 · DOI · Paper page
  48. simonyan, 2014, Very deep convolutional networks for large-scale image recognition, Proc Int Conf Learn Representations
  49. 10.1109/CVPR.2019.00340 · DOI
  50. 10.1109/ICCV.2017.522 · DOI · Paper page

Cited by

See all 3,385

Metadata

Authors
Gao, S.-H., Cheng, M.-M., Zhao, K., Zhang, X.-Y., Yang, M.-H., & Torr, P.
Venue
IEEE Transactions on Pattern Analysis and Machine Intelligence
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Published
2021-02-01
Volume
43
Issue
2
Pages
652-662
ISSN
  • 0162-8828 (ISSN-L)
  • 2160-9292
  • 1939-3539
DOI
10.1109/tpami.2019.2938758
OpenAlex
W2928165649
Cited by
3,385
References
21
FWCI
120.66
Type
journal article
Language
en
Open access
green
Licence
Funders
  • National Natural Science Foundation of China (61620106008, 61572264)
  • national youth talent support program
  • Natural Science Foundation of Tianjin City (17JCJQJC43700, 18ZXZNGX00110)

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Res2Net: A New Multi-Scale Backbone Architecture. https://app.cochat.ai/papers/10.1109/tpami.2019.2938758
The paper
Gao, S.-H., Cheng, M.-M., Zhao, K., Zhang, X.-Y., Yang, M.-H., & Torr, P. (2021). Res2Net: A New Multi-Scale Backbone Architecture. IEEE Transactions on Pattern Analysis and Machine Intelligence. https://doi.org/10.1109/tpami.2019.2938758

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.