亲爱的研友该休息了!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!身体可是革命的本钱,早点休息,好梦!

Transformer-Based Approach Via Contrastive Learning for Zero-Shot Detection

计算机科学 人工智能 变压器 模式识别(心理学) 零(语言学) 工程类 电气工程 语言学 哲学 电压
作者
Wei Liu,Hui Chen,Yongqiang Ma,Jianji Wang,Nanning Zheng
出处
期刊:International Journal of Neural Systems [World Scientific]
卷期号:33 (07) 被引量:5
标识
DOI:10.1142/s0129065723500351
摘要

Zero-shot detection (ZSD) aims to locate and classify unseen objects in pictures or videos by semantic auxiliary information without additional training examples. Most of the existing ZSD methods are based on two-stage models, which achieve the detection of unseen classes by aligning object region proposals with semantic embeddings. However, these methods have several limitations, including poor region proposals for unseen classes, lack of consideration of semantic representations of unseen classes or their inter-class correlations, and domain bias towards seen classes, which can degrade overall performance. To address these issues, the Trans-ZSD framework is proposed, which is a transformer-based multi-scale contextual detection framework that explicitly exploits inter-class correlations between seen and unseen classes and optimizes feature distribution to learn discriminative features. Trans-ZSD is a single-stage approach that skips proposal generation and performs detection directly, allowing the encoding of long-term dependencies at multiple scales to learn contextual features while requiring fewer inductive biases. Trans-ZSD also introduces a foreground-background separation branch to alleviate the confusion of unseen classes and backgrounds, contrastive learning to learn inter-class uniqueness and reduce misclassification between similar classes, and explicit inter-class commonality learning to facilitate generalization between related classes. Trans-ZSD addresses the domain bias problem in end-to-end generalized zero-shot detection (GZSD) models by using balance loss to maximize response consistency between seen and unseen predictions, ensuring that the model does not bias towards seen classes. The Trans-ZSD framework is evaluated on the PASCAL VOC and MS COCO datasets, demonstrating significant improvements over existing ZSD models.
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
Xw发布了新的文献求助10
2秒前
寒冷的应助核桃采纳,获得30
17秒前
wen发布了新的文献求助10
34秒前
隐形曼青应助科研通管家采纳,获得10
43秒前
科研通AI2S应助科研通管家采纳,获得10
43秒前
MchemG应助科研通管家采纳,获得10
43秒前
wen完成签到,获得积分10
46秒前
48秒前
49秒前
50秒前
yar应助wen采纳,获得10
50秒前
核桃发布了新的文献求助30
53秒前
迷人问兰发布了新的文献求助10
58秒前
1分钟前
牛牛完成签到 ,获得积分10
2分钟前
时间煮雨我煮鱼完成签到,获得积分10
2分钟前
Plum22发布了新的文献求助10
2分钟前
BiuBiu怪完成签到,获得积分10
3分钟前
bkagyin应助陈苗采纳,获得10
3分钟前
核桃发布了新的文献求助10
3分钟前
Plum22完成签到 ,获得积分10
4分钟前
自由觅松发布了新的文献求助20
4分钟前
4分钟前
核桃发布了新的文献求助10
4分钟前
深情安青应助科研通管家采纳,获得10
4分钟前
科研通AI2S应助科研通管家采纳,获得10
4分钟前
阳阳阳发布了新的文献求助10
4分钟前
阳阳阳完成签到,获得积分10
4分钟前
5分钟前
5分钟前
CATH完成签到 ,获得积分10
5分钟前
5分钟前
zhanghao发布了新的文献求助10
5分钟前
Hillson完成签到,获得积分10
5分钟前
糯糯完成签到 ,获得积分10
5分钟前
5分钟前
自由飞阳完成签到,获得积分10
5分钟前
小羡完成签到 ,获得积分10
6分钟前
滕皓轩完成签到 ,获得积分20
6分钟前
aDou完成签到 ,获得积分10
6分钟前
高分求助中
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
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 3990084
求助须知:如何正确求助?哪些是违规求助? 3532108
关于积分的说明 11256447
捐赠科研通 3271016
什么是DOI,文献DOI怎么找? 1805171
邀请新用户注册赠送积分活动 882270
科研通“疑难数据库(出版商)”最低求助积分说明 809228