mlsanityData to 7 Oct 2026

D^2ETR: Decoder-Only DETR with Computationally Efficient Cross-Scale Attention

arXiv 2203.00860 ↗First posted 2 Mar 2022cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

DETR is the first fully end-to-end detector that predicts a final set of predictions without post-processing. However, it suffers from problems such as low performance and slow convergence. A series of works aim to tackle these issues in different ways, but the computational cost is yet expensive due to the sophisticated encoder-decoder architecture. To alleviate this issue, we propose a decoder-only detector called D^2ETR. In the absence of encoder, the decoder directly attends to the fine-fused feature maps generated by the Transformer backbone with a novel computationally efficient cross-scale attention module. D^2ETR demonstrates low computational complexity and high detection accuracy in evaluations on the COCO benchmark, outperforming DETR and its variants.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 25 of its 28 references that are in the map. First posted on arXiv 2 Mar 2022.

Builds on

25 of 28 references.

References · 25

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  6. 2020End-to-End Object Detection with Transformerscited by 7,384
  7. 2017Mask R-CNNcited by 7,259
  8. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  9. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  10. 2018YOLOv3: An Incremental Improvementcited by 2,652
  11. 2017Decoupled Weight Decay Regularizationcited by 1,722
  12. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
13 more
  1. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  2. 2018Path Aggregation Network for Instance Segmentationcited by 796
  3. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 749
  4. 2021Conditional DETR for Fast Training Convergencecited by 422
  5. 2021Pix2seq: A Language Modeling Framework for Object Detectioncited by 345
  6. 2019NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detectioncited by 289
  7. 2021Fast Convergence of DETR with Spatially Modulated Co-Attentioncited by 176
  8. 2021You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detectioncited by 170
  9. 2020Rethinking Transformer-based Set Prediction for Object Detectioncited by 156
  10. 2021All Tokens Matter: Token Labeling for Training Better Vision Transformerscited by 144
  11. 2021Efficient DETR: Improving End-to-End Object Detector with Dense Priorcited by 128
  12. 2020End-to-End Object Detection with Adaptive Clustering Transformercited by 109
  13. 2019IoU-aware Single-stage Object Detector for Accurate Localizationcited by 36

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 5; 2024: 3; 2025: 2.

12 papers.

  1. 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 526
  2. 2023Lite DETR : An Interleaved Multi-Scale Encoder for Efficient DETRcited by 36
  3. 2023Object Detection with Transformers: A Reviewcited by 22
  4. 2022A Guide to Image and Video based Small Object Detection using Deep Learning : Case Study of Maritime Surveillancecited by 14
  5. 2022An Extendable, Efficient and Effective Transformer-based Object Detectorcited by 5
  6. 2023Align-DETR: Enhancing End-to-end Object Detection with Aligned Losscited by 5
  7. 2024Practical Video Object Detection via Feature Selection and Aggregationcited by 5
  8. 2025QORT-Former: Query-optimized Real-time Transformer for Understanding Two Hands Manipulating Objectscited by 3
  9. 2023DecoderTracker: Decoder-Only Method for Multiple-Object Trackingcited by 2
  10. 2024Understanding differences in applying DETR to natural and medical imagescited by 2
  11. 2024Mr. DETR++: Instructive Multi-Route Training for Detection Transformers with Mixture-of-Expertscited by 1
  12. 2025Learning Attribute-Aware Hash Codes for Fine-Grained Image Retrieval via Query Optimizationcited by 1