mlsanityData to 14 Oct 2026

DETR++: Taming Your Multi-Scale Detection Transformer

arXiv 2206.02977 ↗First posted 7 Jun 2022cs.CV cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Convolutional Neural Networks (CNN) have dominated the field of detection ever since the success of AlexNet in ImageNet classification [12]. With the sweeping reform of Transformers [27] in natural language processing, Carion et al. [2] introduce the Transformer-based detection method, i.e., DETR. However, due to the quadratic complexity in the self-attention mechanism in the Transformer, DETR is never able to incorporate multi-scale features as performed in existing CNN-based detectors, leading to inferior results in small object detection. To mitigate this issue and further improve performance of DETR, in this work, we investigate different methods to incorporate multi-scale features and find that a Bi-directional Feature Pyramid (BiFPN) works best with DETR in further raising the detection precision. With this discovery, we propose DETR++, a new architecture that improves detection results by 1.9% AP on MS COCO 2017, 11.5% AP on RICO icon detection, and 9.1% AP on RICO layout extraction over existing baselines.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 28 of its 35 references that are in the map. First posted on arXiv 7 Jun 2022.

Builds on

28 of 35 references.

References · 28

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  6. 2020End-to-End Object Detection with Transformerscited by 7,414
  7. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  8. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  9. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  10. 2015Fast R-CNNcited by 2,933
  11. 2018YOLOv3: An Incremental Improvementcited by 2,659
  12. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
16 more
  1. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,577
  2. 2016YOLO9000: Better, Faster, Strongercited by 1,431
  3. 2019Objects as Pointscited by 1,175
  4. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,020
  5. 2018Path Aggregation Network for Instance Segmentationcited by 798
  6. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
  7. 2019NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detectioncited by 291
  8. 2019RAVEN: A Dataset for Relational and Analogical Visual rEasoNingcited by 226
  9. 2021UIBert: Learning Generic Multimodal Representations for UI Understandingcited by 95
  10. 2020Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sensecited by 62
  11. 2019Learning Perceptual Inference by Contrastingcited by 57
  12. 2020ActionBert: Leveraging User Actions for Semantic Understanding of User Interfacescited by 43
  13. 2021Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and Executioncited by 43
  14. 2021ACRE: Abstract Causal REasoning Beyond Covariationcited by 30
  15. 2021Learning Algebraic Representation for Systematic Generalization in Abstract Reasoningcited by 27
  16. 2020Machine Number Sense: A Dataset of Visual Arithmetic Problems for Abstract and Relational Reasoningcited by 18

Built on by

Cited by year

Citing papers per year: 2023: 4.

4 papers.

  1. 2023End-to-End 3D Dense Captioning with Vote2Cap-DETRcited by 78
  2. 2023Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioningcited by 39
  3. 2023Lite DETR : An Interleaved Multi-Scale Encoder for Efficient DETRcited by 36
  4. 2023Transformers in Small Object Detection: A Benchmark and Survey of State-of-the-Artcited by 15