Log In Sign Up

Probabilistic Ranking-Aware Ensembles for Enhanced Object Detections

by   Mingyuan Mao, et al.

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.


page 1

page 2

page 3

page 4


Location-Aware Box Reasoning for Anchor-Based Single-Shot Object Detection

In the majority of object detection frameworks, the confidence of instan...

CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloud

Existing single-stage detectors for locating objects in point clouds oft...

ALFA: Agglomerative Late Fusion Algorithm for Object Detection

We propose ALFA - a novel late fusion algorithm for object detection. AL...

Location-Aware Feature Selection for Scene Text Detection

Direct regression-based natural scene text detection methods have alread...

Generating Positive Bounding Boxes for Balanced Training of Object Detectors

Two-stage deep object detectors generate a set of regions-of-interest (R...

Towards Toxic and Narcotic Medication Detection with Rotated Object Detector

Recent years have witnessed the advancement of deep learning vision tech...

Deformable Distributed Multiple Detector Fusion for Multi-Person Tracking

This paper addresses fully automated multi-person tracking in complex en...