CAT:A Simple yet Effective Cross-Attention Transformer for One-Shot Object Detection

扫码查看

原文链接

万方数据

外文摘要：Given a query patch from a novel class,one-shot object detection aims to detect all instances of this class in a target image through the semantic similarity comparison.However,due to the extremely limited guidance in the novel class as well as the unseen appearance difference between the query and target instances,it is difficult to appropriately ex-ploit their semantic similarity and generalize well.To mitigate this problem,we present a universal Cross-Attention Transformer(CAT)module for accurate and efficient semantic similarity comparison in one-shot object detection.The proposed CAT utilizes the transformer mechanism to comprehensively capture bi-directional correspondence between any paired pixels from the query and the target image,which empowers us to sufficiently exploit their semantic characteristics for accurate similarity comparison.In addition,the proposed CAT enables feature dimensionality compression for infer-ence speedup without performance loss.Extensive experiments on three object detection datasets MS-COCO,PASCAL VOC and FSOD under the one-shot setting demonstrate the effectiveness and efficiency of our model,e.g.,it surpasses CoAE,a major baseline in this task,by 1.0％in average precision(AP)on MS-COCO and runs nearly 2.5 times faster.

外文关键词：

one-shot object detectionTransformerattention mechanism

作者：

林蔚东、邓玉岩、高扬、王宁、刘凌峤、张磊、王鹏

展开 >

作者单位：

School of Computer Science,Northwestern Polytechnical University,Xi'an,710000,China

National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology,Northwestern Polytechnical University,Xi'an,710000,China

School of Computer Science,The University of Adelaide,Adelaide,SA 0115,Australia

基金：

National Science and Technology Major ProjectNational Natural Science Foundation of ChinaNational Natural Science Foundation of ChinaShaanxi Provincial Key Research and Development Program of ChinaNatural Science Basic Research Program of Shaanxi Province of China

项目编号：

2020AAA0106900U19B2307618761522021KWZ-032021JCW-03

出版年：

2024

DOI：

10.1007/s11390-024-1743-6

计算机科学技术学报(英文版)

中国计算机学会

计算机科学技术学报(英文版)

CSTPCD

影响因子：0.432

ISSN：1000-9000

年,卷(期)：2024.39(2)