JOINT PAIRWISE LEARNING AND IMAGE CLUSTERING BASED ON A SIAMESE CNN | Faculty Open Information System

JOINT PAIRWISE LEARNING AND IMAGE CLUSTERING BASED ON A SIAMESE CNN

in International Symposium (oral presentation paper), 國際研討會(全文口頭發表)
標題JOINT PAIRWISE LEARNING AND IMAGE CLUSTERING BASED ON A SIAMESE CNN
出版類型國際研討會(全文口頭發表)
出版年度2018
AuthorsWengtai Su, 蘇翁台, Chih-Chung Hsu 許志仲, Ziling Huang 黃子凌, Chia-Wen Lin 林嘉文, & Cheung G.
出版日期Oct 10 2018 12:0
會議地點Athens
其他編號0000
中文摘要

How to using a deep convolutional neural network (CNN)
to efficiently and effectively learn representations of a large
unlabeled set of images and group them into clusters remains
a challenging problem. To address this problem, we propose
a Siamese clustering CNN (SC-CNN) to iteratively learn
discriminative representations for image clustering. Based
on the proposed SC-CNN, we propose a mini-batch-based
joint pairwise representation learning and clustering scheme
to make the computation and storage cost efficient for largescale
image clustering on a personal computer with a commercial
GPU graphic card. On top of SC-CNN, the proposed
pairwise learning scheme effectively learns discriminative
representations by appropriately selecting same-cluster and
different-cluster image pairs from the results of each clustering
iteration. Experimental results demonstrate that the proposed
method outperforms start-of-the-art clustering schemes
in clustering accuracy on public image sets.

校址:912 屏東縣內埔鄉學府路1號 總機:886-8-7703202 傳真:886-8-7740165 系統開發統維護單位:國立屏東科技大學 電算中心 版權所有