Efficient DETR: Improving End-to-End Object Detector with Dense Prior

The recently proposed end-to-end transformer detectors, such as DETR and Deformable DETR, have a cascade structure of stacking 6 decoder layers to update object queries iteratively, without which their performance degrades seriously. In this paper, we investigate that the random initialization of object containers, which include object queries and reference points, is mainly responsible for the requirement of multiple iterations. Based on our findings, we propose Efficient DETR, a simple and efficient pipeline for end-to-end object detection. By taking advantage of both dense detection and sparse set detection, Efficient DETR leverages dense prior to initialize the object containers and brings the gap of the 1-decoder structure and 6-decoder structure. Experiments conducted on MS COCO show that our method, with only 3 encoder layers and 1 decoder layer, achieves competitive performance with state-of-the-art object detection methods. Efficient DETR is also robust in crowded scenes. It outperforms modern detectors on CrowdHuman dataset by a large margin.

[1]  Larry S. Davis,et al.  Learning From Noisy Anchors for One-Stage Object Detection , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Yi Jiang,et al.  Sparse R-CNN: End-to-End Object Detection with Learnable Proposals , 2020, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Nicolas Usunier,et al.  End-to-End Object Detection with Transformers , 2020, ECCV.

[4]  Benjin Zhu,et al.  AutoAssign: Differentiable Label Assignment for Dense Object Detection , 2020, ArXiv.

[5]  Yiming Yang,et al.  Rethinking Transformer-based Set Prediction for Object Detection , 2020, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[6]  Hao Chen,et al.  FCOS: Fully Convolutional One-Stage Object Detection , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[7]  Kaiming He,et al.  Feature Pyramid Networks for Object Detection , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Yi Li,et al.  Deformable Convolutional Networks , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[10]  Qi Tian,et al.  CenterNet: Keypoint Triplets for Object Detection , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[11]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[13]  Hei Law,et al.  CornerNet: Detecting Objects as Paired Keypoints , 2018, ECCV.

[14]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[15]  Yi Li,et al.  R-FCN: Object Detection via Region-based Fully Convolutional Networks , 2016, NIPS.

[16]  Han Qiu,et al.  BorderDet: Border Feature for Dense Object Detection , 2020, ECCV.

[17]  Hongbin Sun,et al.  End-to-End Object Detection with Fully Convolutional Network , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Andrew Y. Ng,et al.  End-to-End People Detection in Crowded Scenes , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Hee Seok Lee,et al.  Probabilistic Anchor Assignment with IoU Prediction for Object Detection , 2020, ECCV.

[20]  Kaiming He,et al.  Focal Loss for Dense Object Detection , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[21]  Ross B. Girshick,et al.  Mask R-CNN , 2017, 1703.06870.

[22]  Silvio Savarese,et al.  Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Junying Chen,et al.  UP-DETR: Unsupervised Pre-training for Object Detection with Transformers , 2020, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Luc Van Gool,et al.  Dynamic Filter Networks , 2016, NIPS.

[25]  Ross B. Girshick,et al.  Focal Loss for Dense Object Detection , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[26]  Nuno Vasconcelos,et al.  Cascade R-CNN: Delving Into High Quality Object Detection , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[27]  Р Ю Чуйков,et al.  Обнаружение транспортных средств на изображениях загородных шоссе на основе метода Single shot multibox Detector , 2017 .

[28]  Rongrong Ji,et al.  FreeAnchor: Learning to Match Anchors for Visual Object Detection , 2019, NeurIPS.

[29]  Yi Yang,et al.  DenseBox: Unifying Landmark Localization with End to End Object Detection , 2015, ArXiv.

[30]  Peng Gao,et al.  Fast Convergence of DETR with Spatially Modulated Co-Attention , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[31]  Chang D. Yoo,et al.  Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution , 2019, NeurIPS.

[32]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[33]  Bin Li,et al.  Deformable DETR: Deformable Transformers for End-to-End Object Detection , 2020, ICLR.

[34]  Stephen Lin,et al.  Deformable ConvNets V2: More Deformable, Better Results , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[35]  Shifeng Zhang,et al.  Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[36]  Harold W. Kuhn,et al.  The Hungarian method for the assignment problem , 1955, 50 Years of Integer Programming.

[37]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[38]  Xiangyu Zhang,et al.  CrowdHuman: A Benchmark for Detecting Human in a Crowd , 2018, ArXiv.

[39]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[40]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[41]  Ali Farhadi,et al.  YOLOv3: An Incremental Improvement , 2018, ArXiv.

[42]  Ali Farhadi,et al.  YOLO9000: Better, Faster, Stronger , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[43]  Xingyi Zhou,et al.  Objects as Points , 2019, ArXiv.

[44]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[45]  Shifeng Zhang,et al.  Single-Shot Refinement Neural Network for Object Detection , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.