Probabilistic Ranking-Aware Ensembles for Enhanced Object Detections

• URL: http://arxiv.org/abs/2105.03139v1
• Date: Fri, 7 May 2021 09:37:06 GMT
• Title: Probabilistic Ranking-Aware Ensembles for Enhanced Object Detections
• Authors: Mingyuan Mao, Baochang Zhang, David Doermann, Jie Guo, Shumin Han, Yuan Feng, Xiaodi Wang, Errui Ding
• Abstract summary: We propose a novel ensemble called the Probabilistic Ranking Aware Ensemble (PRAE) that refines the confidence of bounding boxes from detectors. We also introduce a bandit approach to address the confidence imbalance problem caused by the need to deal with different numbers of boxes.
• Score: 50.096540945099704
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Model ensembles are becoming one of the most effective approaches for improving object detection performance already optimized for a single detector. Conventional methods directly fuse bounding boxes but typically fail to consider proposal qualities when combining detectors. This leads to a new problem of confidence discrepancy for the detector ensembles. The confidence has little effect on single detectors but significantly affects detector ensembles. To address this issue, we propose a novel ensemble called the Probabilistic Ranking Aware Ensemble (PRAE) that refines the confidence of bounding boxes from detectors. By simultaneously considering the category and the location on the same validation set, we obtain a more reliable confidence based on statistical probability. We can then rank the detected bounding boxes for assembly. We also introduce a bandit approach to address the confidence imbalance problem caused by the need to deal with different numbers of boxes at different confidence levels. We use our PRAE-based non-maximum suppression (P-NMS) to replace the conventional NMS method in ensemble learning. Experiments on the PASCAL VOC and COCO2017 datasets demonstrate that our PRAE method consistently outperforms state-of-the-art methods by significant margins.

Related papers

• Combine and Conquer: A Meta-Analysis on Data Shift and Out-of-Distribution Detection [30.377446496559635]
  This paper introduces a universal approach to seamlessly combine out-of-distribution (OOD) detection scores. Our framework is easily for future developments in detection scores and stands as the first to combine decision boundaries in this context.
  arXiv  Detail & Related papers  (2024-06-23T08:16:44Z)
• Bounding Box Stability against Feature Dropout Reflects Detector Generalization across Environments [52.65013932553849]
  Good detectors tend to output bounding boxes whose locations do not change much, while bounding boxes of poor detectors will undergo noticeable position changes. We compute the box stability score (BoS score) to reflect this stability. We contribute to finding that BoS score has a strong, positive correlation with detection accuracy measured by mean average precision (mAP) under various test environments.
  arXiv  Detail & Related papers  (2024-03-20T17:59:16Z)
• Rank-DETR for High Quality Object Detection [52.82810762221516]
  A highly performant object detector requires accurate ranking for the bounding box predictions. In this work, we introduce a simple and highly performant DETR-based object detector by proposing a series of rank-oriented designs.
  arXiv  Detail & Related papers  (2023-10-13T04:48:32Z)
• Binary Classification with Confidence Difference [100.08818204756093]
  This paper delves into a novel weakly supervised binary classification problem called confidence-difference (ConfDiff) classification. We propose a risk-consistent approach to tackle this problem and show that the estimation error bound the optimal convergence rate. We also introduce a risk correction approach to mitigate overfitting problems, whose consistency and convergence rate are also proven.
  arXiv  Detail & Related papers  (2023-10-09T11:44:50Z)
• Localization-Guided Track: A Deep Association Multi-Object Tracking Framework Based on Localization Confidence of Detections [4.565826090373598]
  localization confidence is applied in MOT for the first time, with appearance clarity and localization accuracy of detection boxes taken into account. Our proposed method outperforms the compared state-of-art tracking methods.
  arXiv  Detail & Related papers  (2023-09-18T13:45:35Z)
• Conservative Prediction via Data-Driven Confidence Minimization [70.93946578046003]
  In safety-critical applications of machine learning, it is often desirable for a model to be conservative. We propose the Data-Driven Confidence Minimization framework, which minimizes confidence on an uncertainty dataset.
  arXiv  Detail & Related papers  (2023-06-08T07:05:36Z)
• ConfMix: Unsupervised Domain Adaptation for Object Detection via Confidence-based Mixing [32.679280923208715]
  Unsupervised Domain Adaptation (UDA) for object detection aims to adapt a model trained on a source domain to detect instances from a new target domain for which annotations are not available. We propose ConfMix, the first method that introduces a sample mixing strategy based on region-level detection confidence for adaptive object detector learning.
  arXiv  Detail & Related papers  (2022-10-20T19:16:39Z)
• Mitigating the Mutual Error Amplification for Semi-Supervised Object Detection [92.52505195585925]
  We propose a Cross Teaching (CT) method, aiming to mitigate the mutual error amplification by introducing a rectification mechanism of pseudo labels. In contrast to existing mutual teaching methods that directly treat predictions from other detectors as pseudo labels, we propose the Label Rectification Module (LRM)
  arXiv  Detail & Related papers  (2022-01-26T03:34:57Z)
• Localization Uncertainty-Based Attention for Object Detection [8.154943252001848]
  We propose a more efficient uncertainty-aware dense detector (UADET) that predicts four-directional localization uncertainties via Gaussian modeling. Experiments using the MS COCO benchmark show that our UADET consistently surpasses baseline FCOS, and that our best model, ResNext-64x4d-101-DCN, obtains a single model, single-scale AP of 48.3% on COCO test-dev.
  arXiv  Detail & Related papers  (2021-08-25T04:32:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.