Decoupled Metric Network for Single-Stage Few-Shot Object Detection

计算机科学 公制(单位) 人工智能 弹丸 对象(语法) 阶段(地层学) 单发 拓扑(电路) 数学 工程类 组合数学 地质学 材料科学 物理 光学 古生物学 冶金 运营管理
作者
Yue Lu,Xingyu Chen,Zhengxing Wu,Junzhi Yu
出处
期刊:IEEE transactions on cybernetics [Institute of Electrical and Electronics Engineers]
卷期号:53 (1): 514-525 被引量:28
标识
DOI:10.1109/tcyb.2022.3149825
摘要

Within the last few years, great efforts have been made to study few-shot learning. Although general object detection is advancing at a rapid pace, few-shot detection remains a very challenging problem. In this work, we propose a novel decoupled metric network (DMNet) for single-stage few-shot object detection. We design a decoupled representation transformation (DRT) and an image-level distance metric learning (IDML) to solve the few-shot detection problem. The DRT can eliminate the adverse effect of handcrafted prior knowledge by predicting objectness and anchor shape. Meanwhile, to alleviate the problem of representation disagreement between classification and location (i.e., translational invariance versus translational variance), the DRT adopts a decoupled manner to generate adaptive representations so that the model is easier to learn from only a few training data. As for a few-shot classification in the detection task, we design an IDML tailored to enhance the generalization ability. This module can perform metric learning for the whole visual feature, so it can be more efficient than traditional DML due to the merit of parallel inference for multiobjects. Based on the DRT and IDML, our DMNet efficiently realizes a novel paradigm for few-shot detection, called single-stage metric detection. Experiments are conducted on the PASCAL VOC dataset and the MS COCO dataset. As a result, our method achieves state-of-the-art performance in few-shot object detection. The codes are available at https://github.com/yrqs/DMNet .
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
刚刚
谢琉圭发布了新的文献求助10
2秒前
wu发布了新的文献求助10
3秒前
打滚完成签到,获得积分10
4秒前
LJJ发布了新的文献求助10
4秒前
睡觉了完成签到 ,获得积分10
6秒前
量子星尘发布了新的文献求助10
7秒前
乖猫要努力应助精明寻梅采纳,获得10
7秒前
AI完成签到,获得积分10
10秒前
xiaosu发布了新的文献求助30
11秒前
11秒前
谢琉圭完成签到,获得积分10
13秒前
领导范儿应助稳重的若雁采纳,获得10
16秒前
16秒前
17秒前
wu完成签到,获得积分20
17秒前
momo发布了新的文献求助10
18秒前
19秒前
田様应助123采纳,获得10
19秒前
23秒前
zying完成签到,获得积分10
26秒前
27秒前
双楠应助wangjue采纳,获得10
27秒前
32秒前
雪白尔岚发布了新的文献求助10
36秒前
36秒前
36秒前
慕青应助momo采纳,获得10
37秒前
从容冰夏完成签到,获得积分10
39秒前
39秒前
桐桐应助Candy采纳,获得10
40秒前
YR完成签到,获得积分10
42秒前
欧阳月空发布了新的文献求助10
42秒前
周em12_发布了新的文献求助10
43秒前
糊涂涂完成签到 ,获得积分10
43秒前
44秒前
46秒前
Zhang完成签到,获得积分10
47秒前
48秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3989334
求助须知:如何正确求助?哪些是违规求助? 3531428
关于积分的说明 11253936
捐赠科研通 3270119
什么是DOI,文献DOI怎么找? 1804887
邀请新用户注册赠送积分活动 882087
科研通“疑难数据库(出版商)”最低求助积分说明 809173