计算机科学
特征(语言学)
鉴定(生物学)
一致性(知识库)
水准点(测量)
人工智能
机器学习
成对比较
公制(单位)
相似性(几何)
排队论
编码(内存)
模式识别(心理学)
数据挖掘
图像(数学)
计算机网络
哲学
语言学
植物
运营管理
大地测量学
经济
生物
地理
作者
Chuchu Han,Zhedong Zheng,Changxin Gao,Changxin Gao,Yi Yang
出处
期刊:Proceedings of the ... AAAI Conference on Artificial Intelligence
[Association for the Advancement of Artificial Intelligence (AAAI)]
日期:2021-05-18
卷期号:35 (2): 1505-1512
被引量:22
标识
DOI:10.1609/aaai.v35i2.16241
摘要
The goal of person search is to localize and match query persons from scene images. For high efficiency, one-step methods have been developed to jointly handle the pedestrian detection and identification sub-tasks using a single network. There are two major challenges in the current one-step approaches. One is the mutual interference between the optimization objectives of multiple sub-tasks. The other is the sub-optimal identification feature learning caused by small batch size when end-to-end training. To overcome these problems, we propose a decoupled and memory-reinforced network (DMRNet). Specifically, to reconcile the conflicts of multiple objectives, we simplify the standard tightly coupled pipelines and establish a deeply decoupled multi-task learning framework. Further, we build a memory-reinforced mechanism to boost the identification feature learning. By queuing the identification features of recently accessed instances into a memory bank, the mechanism augments the similarity pair construction for pairwise metric learning. For better encoding consistency of the stored features, a slow-moving average of the network is applied for extracting these features. In this way, the dual networks reinforce each other and converge to robust solution states. Experimentally, the proposed method obtains 93.2% and 46.9% mAP on CUHK-SYSU and PRW datasets, which exceeds all the existing one-step methods.
科研通智能强力驱动
Strongly Powered by AbleSci AI