Imaginary-Connected Embedding in Complex Space for Unseen Attribute-Object Discrimination

嵌入 想象中的 人工智能 对象(语法) 空格(标点符号) 计算机科学 视觉对象识别的认知神经科学 模式识别(心理学) 计算机视觉 数学 心理学 操作系统 心理治疗师
作者
Chenyi Jiang,Shidong Wang,Yang Long,Zechao Li,Haofeng Zhang,Ling Shao
出处
期刊:IEEE Transactions on Pattern Analysis and Machine Intelligence [IEEE Computer Society]
卷期号:: 1-18
标识
DOI:10.1109/tpami.2024.3487631
摘要

Compositional Zero-Shot Learning (CZSL) aims to recognize novel compositions of seen primitives. Prior studies have attempted to either learn primitives individually (non-connected) or establish dependencies among them in the composition (fully-connected). In contrast, human comprehension of composition diverges from the aforementioned methods as humans possess the ability to make composition-aware adaptation for these primitives, instead of inferring them rigidly through the aforementioned methods. However, developing a comprehension of compositions akin to human cognition proves challenging within the confines of real space. This arises from the limitation of real-space-based methods, which often categorize attributes, objects, and compositions using three independent measures, without establishing a direct dynamic connection. To tackle this challenge, we expand the CZSL distance metric scheme to encompass complex spaces to unify the independent measures, and we establish an imaginary-connected embedding in complex space to model human understanding of attributes. To achieve this representation, we introduce an innovative visual bias-based attribute extraction module that selectively extracts attributes based on object prototypes. As a result, we are able to incorporate phase information in training and inference, serving as a metric for attribute-object dependencies while preserving the independent acquisition of primitives. We evaluate the effectiveness of our proposed approach on three benchmark datasets, illustrating its superiority compared to baseline methods. Our code is available at https://github.com/LanchJL/IMAX.
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
1秒前
1秒前
ClaudiaCY发布了新的文献求助10
2秒前
candy发布了新的文献求助10
2秒前
豆芽完成签到,获得积分10
2秒前
pluto应助wml采纳,获得10
3秒前
iui飞完成签到,获得积分10
3秒前
3秒前
IyGnauH完成签到 ,获得积分10
4秒前
4秒前
6秒前
小巧的虔发布了新的文献求助10
6秒前
iui飞发布了新的文献求助10
6秒前
科研通AI2S应助jiang采纳,获得10
6秒前
小青龙完成签到,获得积分10
7秒前
ws完成签到,获得积分20
8秒前
8秒前
天天快乐应助1234采纳,获得10
9秒前
PRIPRO发布了新的文献求助10
9秒前
萧萧完成签到,获得积分10
9秒前
Akim应助小小小何77采纳,获得10
9秒前
shinysparrow应助烟波钓客采纳,获得200
10秒前
hetao286发布了新的文献求助10
10秒前
脑洞疼应助乐观的忘幽采纳,获得10
11秒前
泰裤辣完成签到,获得积分10
11秒前
勤劳太阳发布了新的文献求助10
14秒前
regene完成签到,获得积分10
14秒前
HelloKun发布了新的文献求助10
14秒前
wml完成签到 ,获得积分10
15秒前
LaTeXer应助平常囧采纳,获得50
15秒前
dingz完成签到,获得积分10
19秒前
可爱的函函应助七七采纳,获得10
19秒前
赘婿应助爱听歌初曼采纳,获得10
19秒前
21秒前
21秒前
22秒前
万能图书馆应助自信河马采纳,获得10
22秒前
小蘑菇应助易昭华采纳,获得10
23秒前
xkyasc发布了新的文献求助10
25秒前
小圆发布了新的文献求助10
25秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
Toward a Combinatorial Approach for the Prediction of IgG Half-Life and Clearance 500
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
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 3969940
求助须知:如何正确求助?哪些是违规求助? 3514642
关于积分的说明 11175298
捐赠科研通 3249947
什么是DOI,文献DOI怎么找? 1795178
邀请新用户注册赠送积分活动 875617
科研通“疑难数据库(出版商)”最低求助积分说明 804891