Learning deep discriminative representations with pseudo supervision for image clustering
Learning deep discriminative representations with pseudo supervision for image clustering
复制标题
通过图像聚类的伪监督学习深度判别表示
DOI：
10.1016/j.ins.2021.03.066
复制
发表时间：
2021-04
影响因子：
8.1
通讯作者：
Du Yunfei
中科院分区：
文献类型：
--
作者：
Hu Weibo;Chen Chuan;Ye Fanghua;Zheng Zibin;Du Yunfei
图像聚类是机器学习和计算机视觉中一项至关重要但具有挑战性的任务。其性能很大程度上取决于图像特征表示的质量。最近，将表示学习与聚类相结合的深度联合聚类呈现出了令人鼓舞的性能。然而，现有的联合方法存在两个严重的问题。也就是说，学习到的表示缺乏可辨别性，尤其是对于复杂的图像，并且由于缺乏监督信息而导致性能经常遇到瓶颈。为了解决这些问题，我们提出了一种伪监督联合图像聚类方法，即判别性伪监督聚类（DPSC）。我们的核心思想是发现并利用伪监督信息为判别表示学习提供监督指导。借助伪监督，可以不断细化表示，以促进簇间可分离性和簇内紧凑性，从而产生更具辨别力的表示和正确分离的簇。为了充分受益于联合学习，我们进一步引入了一种自进化训练算法来联合优化 DPSC 模型，其中随着迭代过程中发现更可靠的伪监督信息，学习到的表示和聚类结果逐渐相互促进。实验结果表明，DPSC 在各种图像数据集上显着优于最先进的方法。此外，学习到的特征表示可以很好地推广到各种算法。
Image clustering is a crucial but challenging task in machine learning and computer vision. Its performance highly depends on the quality of image feature representations. Recently, deep joint clustering which combines representation learning with clustering has presented a promising performance. However, existing joint methods suffer from two severe problems. That is, the learned representations lack discriminability especially for intricate images, and the performance often encounters a bottleneck due to the lack of supervision information. To address these problems, we propose a pseudo-supervised joint method for image clustering, i.e.,Discriminative Pseudo Supervision Clustering(DPSC). Our key idea is to discover and utilize the pseudo supervision information to provide supervisory guidance for discriminative representation learning. With the aid of pseudo supervision, the representations can be continuously refined to facilitate inter-cluster separability and intra-cluster compactness, thereby leading to more discriminative representations and correctly separated clusters. To fully benefit from joint learning, we further introduce a self-evolution training algorithm to jointly optimize the DPSC model, in which the learned representations and clustering results boost each other progressively as more reliable pseudo supervision information is discovered during the iteration. Experimental results show that DPSC significantly outperforms state-of-the-art methods on various image datasets. Moreover, the learned feature representations generalize well across various algorithms.
登录
查看更多内容
DOI：
10.1023/b:visi.0000029664.99615.94
发表时间：
2004-11-01
影响因子：
19.5
作者：
Lowe, DG
通讯作者：
Lowe, DG
影响因子：
3.4
作者：
Fei Tian;Bin Gao;Qing Cui;Enhong Chen;Tie-Yan Liu
通讯作者：
Fei Tian;Bin Gao;Qing Cui;Enhong Chen;Tie-Yan Liu
DOI：
10.5555/1756006.1953039
发表时间：
2010-03
期刊：
J. Mach. Learn. Res.
影响因子：
--
作者：
Pascal Vincent;H. Larochelle;Isabelle Lajoie;Yoshua Bengio;Pierre-Antoine Manzagol
通讯作者：
Pascal Vincent;H. Larochelle;Isabelle Lajoie;Yoshua Bengio;Pierre-Antoine Manzagol
影响因子：
10.6
作者：
Guo, Zhenhua;Zhang, Lei;Zhang, David
通讯作者：
Zhang, David
一种结合重建系数和成对距离的凝聚聚类新相似度
影响因子：
8.1
作者：
Cai, Zhiling;Yang, Xiaofei;Zhu, William
通讯作者：
Zhu, William