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!

Vision Transformer for Contrastive Clustering

计算机科学 特征学习 聚类分析 人工智能 模式识别(心理学) 深度学习 卷积神经网络 自编码
作者
Hua-Bao Ling,Bin Zhu,Hui Dong,Ding-Hua Chen,Chang‐Dong Wang,Jianhuang Lai
出处
期刊:Cornell University - arXiv
标识
DOI:10.48550/arxiv.2206.12925
摘要

Vision Transformer (ViT) has shown its advantages over the convolutional neural network (CNN) with its ability to capture global long-range dependencies for visual representation learning. Besides ViT, contrastive learning is another popular research topic recently. While previous contrastive learning works are mostly based on CNNs, some recent studies have attempted to combine ViT and contrastive learning for enhanced self-supervised learning. Despite the considerable progress, these combinations of ViT and contrastive learning mostly focus on the instance-level contrastiveness, which often overlook the global contrastiveness and also lack the ability to directly learn the clustering result (e.g., for images). In view of this, this paper presents a novel deep clustering approach termed Vision Transformer for Contrastive Clustering (VTCC), which for the first time, to our knowledge, unifies the Transformer and the contrastive learning for the image clustering task. Specifically, with two random augmentations performed on each image, we utilize a ViT encoder with two weight-sharing views as the backbone. To remedy the potential instability of the ViT, we incorporate a convolutional stem to split each augmented sample into a sequence of patches, which uses multiple stacked small convolutions instead of a big convolution in the patch projection layer. By learning the feature representations for the sequences of patches via the backbone, an instance projector and a cluster projector are further utilized to perform the instance-level contrastive learning and the global clustering structure learning, respectively. Experiments on eight image datasets demonstrate the stability (during the training-from-scratch) and the superiority (in clustering performance) of our VTCC approach over the state-of-the-art.

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
21完成签到,获得积分10
3秒前
大个应助科研通管家采纳,获得10
7秒前
7秒前
田様应助科研通管家采纳,获得10
7秒前
7秒前
lu完成签到 ,获得积分10
7秒前
WebCasa完成签到,获得积分10
11秒前
14秒前
Albert发布了新的文献求助10
19秒前
bkagyin应助ming采纳,获得10
19秒前
Albert完成签到,获得积分0
26秒前
本尼脸上褶子完成签到 ,获得积分10
34秒前
36秒前
su完成签到 ,获得积分10
36秒前
稳重霆完成签到 ,获得积分20
37秒前
北城发布了新的文献求助10
43秒前
AA完成签到 ,获得积分10
47秒前
乐观的海莲完成签到,获得积分10
1分钟前
1分钟前
Misa发布了新的文献求助10
1分钟前
健忘的溪灵完成签到 ,获得积分10
1分钟前
2分钟前
无地完成签到 ,获得积分20
2分钟前
北城完成签到,获得积分10
2分钟前
2分钟前
丹丹发布了新的文献求助10
2分钟前
斯文的苡完成签到,获得积分10
2分钟前
2分钟前
冷静的诗蕊完成签到,获得积分10
2分钟前
2分钟前
无地关注了科研通微信公众号
2分钟前
周俊杰完成签到,获得积分10
2分钟前
完美世界应助仕殊采纳,获得10
2分钟前
CodeCraft应助丹丹采纳,获得10
3分钟前
3分钟前
3分钟前
3分钟前
ming发布了新的文献求助10
3分钟前
baba完成签到,获得积分10
3分钟前
baba发布了新的文献求助10
3分钟前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
晶种分解过程与铝酸钠溶液混合强度关系的探讨 8888
Chemistry and Physics of Carbon Volume 18 800
The Organometallic Chemistry of the Transition Metals 800
Leading Academic-Practice Partnerships in Nursing and Healthcare: A Paradigm for Change 800
The formation of Australian attitudes towards China, 1918-1941 640
Signals, Systems, and Signal Processing 610
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 工程类 有机化学 化学工程 生物化学 计算机科学 物理 内科学 复合材料 催化作用 物理化学 光电子学 电极 细胞生物学 基因 无机化学
热门帖子
关注 科研通微信公众号,转发送积分 6426272
求助须知:如何正确求助?哪些是违规求助? 8243658
关于积分的说明 17527121
捐赠科研通 5481100
什么是DOI,文献DOI怎么找? 2894502
邀请新用户注册赠送积分活动 1870586
关于科研通互助平台的介绍 1708887