Exploring Base-Class Suppression with Prior Guidance for Bias-Free One-Shot Object Detection

doi:10.1609/aaai.v38i7.28561

	Exploring Base-Class Suppression with Prior Guidance for Bias-Free One-Shot Object Detection
	Zhang, Wenwen 1; Hu, Yun2 ; Shan, Hangguan 1; Liu, Eryun 1
	2024
会议录名称	PROCEEDINGS OF THE AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE
ISSN	2159-5399
页码	7314-7322
发表状态	已发表
DOI	10.1609/aaai.v38i7.28561
摘要	One-shot object detection (OSOD) aims to detect all object instances towards the given category specified by a query image. Most existing studies in OSOD endeavor to establish effective cross-image correlation with limited query information, however, ignoring the problems of the model bias towards the base classes and the generalization degradation on the novel classes. Observing this, we propose a novel algorithm, namely Base-class Suppression with Prior Guidance (BSPG) network to achieve bias-free OSOD. Specifically, the objects of base categories can be detected by a base-class predictor and eliminated by a base-class suppression module (BcS). Moreover, a prior guidance module (PG) is designed to calculate the correlation of high-level features in a non-parametric manner, producing a class-agnostic prior map with unbiased semantic information to guide the subsequent detection process. Equipped with the proposed two modules, we endow the model with a strong discriminative ability to distinguish the target objects from distractors belonging to the base classes. Extensive experiments show that our method outperforms the previous techniques by a large margin and achieves new state-of-the-art performance under various evaluation settings. Copyright © 2024, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
会议录编者/会议主办者	Association for the Advancement of Artificial Intelligence
关键词	Artificial intelligence Object recognition Semantics Base class Generalisation High-level features Image correlations Model bias Nonparametrics Novel algorithm Objects detection Query images Query information
会议名称	38th AAAI Conference on Artificial Intelligence, AAAI 2024
出版地	2275 E BAYSHORE RD, STE 160, PALO ALTO, CA 94303 USA
会议地点	Vancouver, BC, Canada
会议日期	February 20, 2024 - February 27, 2024
URL	查看原文
收录类别	EI ; CPCI-S
语种	英语
资助项目	Zhejiang Provincial Natural Science Foundation of China[LGF20F010006] ; National Natural Science Foundation of China["U21B2029","U21A20456"]
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Theory & Methods
WOS记录号	WOS:001239937300091
出版者	Association for the Advancement of Artificial Intelligence
EI入藏号	20241515870425
EI主题词	Object detection
EISSN	2374-3468
EI分类号	723.2 Data Processing and Image Processing ; 723.4 Artificial Intelligence
原始文献类型	Conference article (CA)
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/364703
专题	信息科学与技术学院信息科学与技术学院_博士生
通讯作者	Liu, Eryun
作者单位	1.College of Information Science and Electronic Engineering, Zhejiang University, China 2.School of Information Science and Technology, ShanghaiTech University, China
推荐引用方式 GB/T 7714	Zhang, Wenwen,Hu, Yun,Shan, Hangguan,et al. Exploring Base-Class Suppression with Prior Guidance for Bias-Free One-Shot Object Detection[C]//Association for the Advancement of Artificial Intelligence. 2275 E BAYSHORE RD, STE 160, PALO ALTO, CA 94303 USA:Association for the Advancement of Artificial Intelligence,2024:7314-7322.