Probabilistic Ranking-Aware Ensembles for Enhanced Object Detections
arXiv:2105.03139
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.
References in corpus (18)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- YOLOv3: An Incremental Improvement
- Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
- DSSD : Deconvolutional Single Shot Detector
- FCOS: Fully Convolutional One-Stage Object Detection
- MMDetection: Open MMLab Detection Toolbox and Benchmark
- Beyond Skip Connections: Top-Down Modulation for Object Detection
- FreeAnchor: Learning to Match Anchors for Visual Object Detection
- Hybrid Task Cascade for Instance Segmentation
- End-to-End Object Detection with Adaptive Clustering Transformer
- MetaAnchor: Learning to Detect Objects with Customized Anchors
- Bounding Box Regression with Uncertainty for Accurate Object Detection
- Vehicle Traffic Driven Camera Placement for Better Metropolis Security Surveillance
- Fast Convergence of DETR with Spatially Modulated Co-Attention
- 1st Place Solutions for OpenImage2019 -- Object Detection and Instance Segmentation
- The 1st Tiny Object Detection Challenge:Methods and Results
- Improving Object Detection with Inverted Attention
- iffDetector: Inference-aware Feature Filtering for Object Detection