mlsanityData to 7 Oct 2026

End-to-End Multi-Object Detection with a Regularized Mixture Model

arXiv 2205.08714 ↗First posted 18 May 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent end-to-end multi-object detectors simplify the inference pipeline by removing hand-crafted processes such as non-maximum suppression (NMS). However, during training, they still heavily rely on heuristics and hand-crafted processes which deteriorate the reliability of the predicted confidence score. In this paper, we propose a novel framework to train an end-to-end multi-object detector consisting of only two terms: negative log-likelihood (NLL) and a regularization term. In doing so, the multi-object detection problem is treated as density estimation of the ground truth bounding boxes utilizing a regularized mixture density model. The proposed textitend-to-end multi-object Detection with a Regularized Mixture Model (D-RMM) is trained by minimizing the NLL with the proposed regularization term, maximum component maximization (MCM) loss, preventing duplicate predictions. Our method reduces the heuristics of the training process and improves the reliability of the predicted confidence score. Moreover, our D-RMM outperforms the previous end-to-end detectors on MS COCO dataset.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 34 references that are in the map. First posted on arXiv 18 May 2022.

Builds on

23 of 34 references.

References · 23

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  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. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  7. 2017On Calibration of Modern Neural Networkscited by 4,860
  8. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  9. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  10. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  11. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  12. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,361
11 more
  1. 2022DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETRcited by 569
  2. 2020Sparse R-CNN: End-to-End Object Detection with Learnable Proposalscited by 494
  3. 2022DN-DETR: Accelerate DETR Training by Introducing Query DeNoisingcited by 486
  4. 2021Conditional DETR for Fast Training Convergencecited by 422
  5. 2017Relation Networks for Object Detectioncited by 305
  6. 2018Bounding Box Regression with Uncertainty for Accurate Object Detectioncited by 143
  7. 2021Sparse DETR: Efficient End-to-End Object Detection with Learnable Sparsitycited by 98
  8. 2022AdaMixer: A Fast-Converging Query-Based Object Detectorcited by 78
  9. 2017MegDet: A Large Mini-Batch Object Detectorcited by 66
  10. 2021ViDT: An Efficient and Effective Fully Transformer-based Object Detectorcited by 45
  11. 2019Training Multi-Object Detector by Estimating Bounding Box Distribution for Input Imagecited by 3

Built on by

Not cited yet.