mlsanityData to 7 Oct 2026

Cross Resolution Encoding-Decoding For Detection Transformers

arXiv 2410.04088 ↗First posted 5 Oct 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Detection Transformers (DETR) are renowned object detection pipelines, however computationally efficient multiscale detection using DETR is still challenging. In this paper, we propose a Cross-Resolution Encoding-Decoding (CRED) mechanism that allows DETR to achieve the accuracy of high-resolution detection while having the speed of low-resolution detection. CRED is based on two modules; Cross Resolution Attention Module (CRAM) and One Step Multiscale Attention (OSMA). CRAM is designed to transfer the knowledge of low-resolution encoder output to a high-resolution feature. While OSMA is designed to fuse multiscale features in a single step and produce a feature map of a desired resolution enriched with multiscale information. When used in prominent DETR methods, CRED delivers accuracy similar to the high-resolution DETR counterpart in roughly 50% fewer FLOPs. Specifically, state-of-the-art DN-DETR, when used with CRED (calling CRED-DETR), becomes 76% faster, with ~50% reduced FLOPs than its high-resolution counterpart with 202 G FLOPs on MS-COCO benchmark. We plan to release pretrained CRED-DETRs for use by the community. Code: https://github.com/ashishkumar822/CRED-DETR

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 30 of its 32 references that are in the map. First posted on arXiv 5 Oct 2024.

Builds on

30 of 32 references.

References · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2020End-to-End Object Detection with Transformerscited by 7,384
  6. 2016Layer Normalizationcited by 5,579
  7. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  8. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  9. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  10. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  11. 2016Pyramid Scene Parsing Networkcited by 2,472
  12. 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,306
18 more
  1. 2022DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETRcited by 569
  2. 2021CoAtNet: Marrying Convolution and Attention for All Data Sizescited by 566
  3. 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 526
  4. 2020Sparse R-CNN: End-to-End Object Detection with Learnable Proposalscited by 494
  5. 2022DN-DETR: Accelerate DETR Training by Introducing Query DeNoisingcited by 486
  6. 2021Conditional DETR for Fast Training Convergencecited by 422
  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. 2021Efficient DETR: Improving End-to-End Object Detector with Dense Priorcited by 128
  11. 2022Accelerating DETR Convergence via Semantic-Aligned Matchingcited by 58
  12. 2023Lite DETR : An Interleaved Multi-Scale Encoder for Efficient DETRcited by 36
  13. 2024MS-DETR: Efficient DETR Training with Mixed Supervisioncited by 34
  14. 2021Anchor DETR: Query Design for Transformer-Based Object Detectioncited by 30
  15. 2024Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinementcited by 30
  16. 2022Towards Efficient Use of Multi-Scale Features in Transformer-Based Object Detectorscited by 10
  17. 2022SAP-DETR: Bridging the Gap Between Salient Points and Queries-Based Transformer Detector for Fast Model Convergencycited by 9
  18. 2023Siamese DETRcited by 7

Built on by

Not cited yet.