Contrastive learning for unsupervised image-to-image translation

计算机科学 图像(数学) 翻译(生物学) 人工智能 图像翻译 自然语言处理 计算机视觉 模式识别(心理学) 生物化学 基因 信使核糖核酸 化学
作者
Hanbit Lee,Jinseok Seol,Sang-goo Lee,Jaehui Park,Junho Shim
出处
期刊:Applied Soft Computing [Elsevier BV]
卷期号:151: 111170-111170 被引量:6
标识
DOI:10.1016/j.asoc.2023.111170
摘要

Image-to-image translation (I2I) aims to learn a mapping function to transform images into different styles or domains while preserving their key structures. Typically, I2I models require manually defined image domains as a training set to learn the visual differences among the image domains and achieve the ability to translate images across them. However, constructing such multi-domain datasets on a large scale requires expensive data collection and annotation processes. Moreover, if the target domain changes or is expanded, a new dataset should be collected, and the model should be retrained. To address these challenges, this article presents a novel unsupervised I2I method that does not require manually defined image domains. The proposed method automatically learns the visual similarity between individual samples and leverages the learned similarity function to transfer a specific style or appearance across images. Therefore, the developed method does not rely on cost-intensive manual domains or unstable clustering results, leading to improved translation accuracy at minimal cost. For quantitative evaluation, we implemented a state-of-the-art I2I models and performed image transformation on the same input image using the baselines and our method. The image quality was then assessed using two quantitative metrics: Frechet inception distance (FID) and translation accuracy. The proposed method exhibited significant improvements in image quality and translation accuracy compared with the latest unsupervised I2I methods. Specifically, the developed technique achieved a 25% and 19% improvement over the best-performing unsupervised baseline in terms of FID and translation accuracy, respectively. Furthermore, this approach demonstrated performance nearly comparable to those of supervised learning-based methods trained using manually collected and constructed domains.
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
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
纷纭完成签到,获得积分10
刚刚
刚刚
刚刚
1秒前
kehe!完成签到 ,获得积分0
1秒前
蔡蔡蔡发布了新的文献求助10
4秒前
引子完成签到,获得积分10
4秒前
庄海棠完成签到 ,获得积分10
5秒前
点点滴滴发布了新的文献求助10
6秒前
hhhhhh发布了新的文献求助10
7秒前
阔达的铅笔完成签到,获得积分10
7秒前
8秒前
苗条白枫完成签到 ,获得积分10
9秒前
冉冉完成签到 ,获得积分0
9秒前
机灵的鲜花完成签到 ,获得积分10
11秒前
点点滴滴完成签到,获得积分20
11秒前
11秒前
九零后无心完成签到,获得积分10
15秒前
爆米花应助靖哥哥采纳,获得30
16秒前
独行侠完成签到,获得积分10
16秒前
外向钢笔发布了新的文献求助10
17秒前
hhhhhh完成签到,获得积分20
17秒前
华仔应助点点滴滴采纳,获得10
18秒前
完美的沉鱼完成签到 ,获得积分10
18秒前
嗨Honey完成签到 ,获得积分10
19秒前
成成完成签到,获得积分0
19秒前
追梦发布了新的文献求助10
19秒前
21秒前
24秒前
24秒前
24秒前
飞速get完成签到 ,获得积分10
25秒前
科研通AI5应助单纯的手机采纳,获得10
25秒前
25秒前
普萘没有洛尔完成签到 ,获得积分10
25秒前
慢慢子发布了新的文献求助10
27秒前
内向翰完成签到,获得积分10
28秒前
29秒前
碧蓝的睫毛完成签到,获得积分10
29秒前
靖哥哥发布了新的文献求助30
29秒前
高分求助中
Production Logging: Theoretical and Interpretive Elements 2700
Neuromuscular and Electrodiagnostic Medicine Board Review 1000
こんなに痛いのにどうして「なんでもない」と医者にいわれてしまうのでしょうか 510
The First Nuclear Era: The Life and Times of a Technological Fixer 500
Unusual formation of 4-diazo-3-nitriminopyrazoles upon acid nitration of pyrazolo[3,4-d][1,2,3]triazoles 500
岡本唐貴自伝的回想画集 500
Distinct Aggregation Behaviors and Rheological Responses of Two Terminally Functionalized Polyisoprenes with Different Quadruple Hydrogen Bonding Motifs 450
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 物理 生物化学 纳米技术 计算机科学 化学工程 内科学 复合材料 物理化学 电极 遗传学 量子力学 基因 冶金 催化作用
热门帖子
关注 科研通微信公众号,转发送积分 3671619
求助须知:如何正确求助?哪些是违规求助? 3228325
关于积分的说明 9779523
捐赠科研通 2938636
什么是DOI,文献DOI怎么找? 1610158
邀请新用户注册赠送积分活动 760547
科研通“疑难数据库(出版商)”最低求助积分说明 736093