.png){kind=icon}
返回
Scale-balanced loss for object detection
.png){kind=icon}
OA
AI
DOI：10.1016/j.patcog.2021.107997.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Object detection is an important field in computer vision. Nevertheless, a research area that has so far not received much attention is the study into the effectiveness of anchor matching strategy and imbalance in anchor-based object detection, in particular small object detection. It is clear that the objects with larger sizes tend to match more anchors than smaller ones. This matching imbalance may result in poor performance in detecting small objects. It can be alleviated by paying more attention to the objects that match with fewer anchors. We propose an innovative flexible loss function for object detection, which is compatible with popular anchor-based detection methods. The proposed method, called the scale-balanced loss, does not add any extra computational cost to the original pipelines. By re-weighting strategy, the proposed method significantly improves the accuracy of multi-scale object detection, especially for small objects. Comprehensive experiments indicate that the scale-balanced loss achieved excellent generalization performance when separately applied to some popular detection methods. The scale-balanced loss attained up to 15% improvements on recall rates of small and medium objects in both the PASCAL VOC and MS COCO dataset. It is also beneficial to the AP result on MS COCO with an improvement of more than 1.5% . (c) 2021 Elsevier Ltd. All rights reserved.
Keyword:
Object detection
Neural network
Matching imbalance
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Comparative study of layer by layer assembled multilayer films based on graphene oxide and reduced graphene oxide on flexible polyurethane foam: flame retardant and smoke suppression properties.png)
RSC Advances
RSC AdvancesIF0
PREAI
分享收藏MDFN: Multi-scale deep feature learning network for object detectionMDFN: 用于目标检测的多尺度深度特征学习网络PATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏
Deep features for person re-identification on metric learning基于度量学习的人物再识别深度特征PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏分享收藏
查看更多内容