CoChat
Sign Up
Cited by 1,055Advanced Neural Network ApplicationsVisual Attention and Saliency DetectionAdvanced Image and Video Retrieval Techniques

The DOI matches its Crossref record; 56 of the 59 references it cites were found in a registry or an index.

Conditional DETR for Fast Training Convergence

Open access
Meng, Depu, Chen, Xiaokang, Fan, Zejia, Zeng, Gang, Li, Houqiang, Yuan, Yuhui, Sun, Lei, Wang, Jingdong·2021·2021 IEEE/CVF International Conference on Computer Vision (ICCV)
DOI 10.1109/iccv48922.2021.00363
Open this paper in CoChat — free accountOpen PDF

Abstract

The recently-developed DETR approach applies the transformer encoder and decoder architecture to object detection and achieves promising performance. In this paper, we handle the critical issue, slow training convergence, and present a conditional cross-attention mechanism for fast DETR training. Our approach is motivated by that the cross-attention in DETR relies highly on the content embeddings for localizing the four extremities and predicting the box, which increases the need for high-quality content embeddings and thus the training difficulty.Our approach, named conditional DETR, learns a conditional spatial query from the decoder embedding for decoder multi-head cross-attention. The benefit is that through the conditional spatial query, each cross-attention head is able to attend to a band containing a distinct region, e.g., one object extremity or a region inside the object box. This narrows down the spatial range for localizing the distinct regions for object classification and box regression, thus relaxing the dependence on the content embeddings and easing the training. Empirical results show that conditional DETR converges 6.7× faster for the backbones R50 and R101 and 10× faster for stronger backbones DC5-R50 and DC5-R101. Code is available at https://github.com/Atten4Vis/ConditionalDETR.

Overview

Integrity signals

Registry

Crossref · 10.1109/iccv48922.2021.00363

Cites

56 of 56 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.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Show all 59 references

Research works printed but not linked: 1

  1. kong, 2019, Foveabox: Beyond anchor-based object detector, CoRR

Cited by

Sorted by citations

Items 901–1,000 of 1,001

Related

See all

Metadata

Authors
Meng, D., Chen, X., Fan, Z., Zeng, G., Li, H., Yuan, Y., Sun, L., & Wang, J.
Affiliations
  • University of Science and Technology of China (CN)
  • Peking University (CN)
  • Microsoft (United States) (US)
  • Microsoft Research Asia (China) (CN)
ORCID
Venue
2021 IEEE/CVF International Conference on Computer Vision (ICCV)
Publisher
IEEE
Published
2021-10
Pages
3631-3640
DOI
10.1109/iccv48922.2021.00363
OpenAlex
W3194329900
Cited by
1,055
References
59
Citations by year
2026: 222 · 2025: 331 · 2024: 263 · 2023: 174 · 2022: 61 · 2021: 4
FWCI
41.05
Type
conference paper
Language
en
Open access
Licence
Locations
  • IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
  • arXiv (Cornell University) (submittedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University) (cc-by)
Funders
  • Research and Development
  • National Natural Science Foundation of China
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 › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
Keywords
DETR, object detection, cross-attention, training convergence, content embedding, spatial localization, object classification, transformer encoder-decoder

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