CoChat
Sign Up
Cited by 1,080Advanced Neural Network ApplicationsDomain Adaptation and Few-Shot LearningVisual Attention and Saliency Detection

The DOI matches its Crossref record; 79 of the 85 references it cites were found in a registry or an index.

InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions

Open access
Wang, Wenhai, Dai, Jifeng, Chen, Zhe, Huang, Zhenhang, Li, Zhiqi, Zhu, Xizhou, Hu, Xiaowei, Lu, Tong, Lu, Lewei, Li, Hongsheng, Wang, Xiaogang, Qiao, Yu·2023·2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
DOI 10.1109/cvpr52729.2023.01385
Open this paper in CoChat — free accountOpen PDF

Abstract

Compared to the great progress of large-scale vision transformers (ViTs) in recent years, large-scale models based on convolutional neural networks (CNNs) are still in an early state. This work presents a new large-scale CNN-based foundation model, termed InternImage, which can obtain the gain from increasing parameters and training data like ViTs. Different from the recent CNNs that focus on large dense kernels, InternImage takes deformable convolution as the core operator, so that our model not only has the large effective receptive field required for downstream tasks such as detection and segmentation, but also has the adaptive spatial aggregation conditioned by input and task information. As a result, the proposed InternImage reduces the strict inductive bias of traditional CNNs and makes it possible to learn stronger and more robust patterns with large-scale parameters from massive data like ViTs. The effectiveness of our model is proven on challenging benchmarks including ImageNet, COCO, andADE20K. It is worth mentioning that InternImage-H achieved a new record 65.4 mAP on COCO test-dev and 62.9 mIoU on ADE20K, outperforming current leading CNNs and ViTs.

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/cvpr52729.2023.01385

Cites

79 of 79 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

Flagged first, then by citations

Show all 85 references

6 of the 85 references couldn’t be matched to a known paper.

Research works printed but not linked: 3

  1. radford, 2019, Language models are unsu-pervised multitask learners, OpenAIRE blog, 1, 9
  2. chen, 2022, Group detr: Fast training convergence with de-coupled one-to-many label assignment, ArXiv Preprint
  3. liu, 2022, More convnets in the 2020s: Scaling up kernels beyond 51x51 using sparsity, ArXiv Preprint

Cited by

Sorted by citations

Items 701–800 of 1,000

Related

See all

Metadata

Authors
Wang, W., Dai, J., Chen, Z., Huang, Z., Li, Z., Zhu, X., Hu, X., Lu, T., Lu, L., Li, H., Wang, X., & Qiao, Y.
Affiliations
  • Shanghai Artificial Intelligence Laboratory (CN)
  • Sense Time Research
  • Nanjing University
  • Chinese University of Hong Kong (HK)
ORCID
Venue
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2023-06
Pages
14408-14419
ISSN
1063-6919 (ISSN-L)
DOI
10.1109/cvpr52729.2023.01385
OpenAlex
W4386076222
Cited by
1,080
References
85
Citations by year
2026: 197 · 2025: 382 · 2024: 362 · 2023: 138
FWCI
115.39
Type
conference paper
Language
en
Open access
Licence
Locations
  • IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
  • arXiv (Cornell University) (submittedVersion, cc-by)
  • arXiv (Cornell University) (cc-by)
Funders
National Natural Science Foundation of China (61672273,61832008)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
Keywords
deformable convolution, receptive fields, inductive bias, object detection, semantic segmentation, image classification

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