.png){kind=icon}
.png){kind=icon}
Return
Mitigate the classification ambiguity via localization-classification sequence in object detection
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2023.109418.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In anchor-based detectors, the confidence scores and label-assignment results for the classification task are determined by the unrefined anchors rather than the final-refined boxes, which causes classifica-tion ambiguity due to the lack of correlation between the classification and localization tasks. In this paper, we investigate the classification ambiguity thoroughly via extensive experiments, and present the localization-classification sequence detector (LCSDet) that performs localization and classification in or-der, bridging the gap between them. To achieve this, the refinement-aware (RA) classification branch and RA assignment are proposed in LCSDet. In inference, the RA classification branch rectifies the fea-ture misalignment and directly classifies the refined anchors. During training, the RA assignment tackles the training instability, narrows the location-quality gap and assigns the refined anchors to ground-truth objects. Comprehensive experiments indicate that the LCSDet can effectively mitigate the classification ambiguity and achieve stable improvement across different baselines.(c) 2023 Elsevier Ltd. All rights reserved.
Keywords:
Object detection
Classification ambiguity
Refinement -aware classification