CC-LOSS: CHANNEL CORRELATION LOSS FOR IMAGE CLASSIFICATION

doi:10.1109/ICPR48806.2021.9412069

CORC > 兰州理工大学 > 兰州理工大学

	CC-LOSS: CHANNEL CORRELATION LOSS FOR IMAGE CLASSIFICATION
	Song, Zeyu 1; Chang, Dongliang 1; Ma, Zhanyu 1; Li, Xiaoxu 2; Tan, Zheng-Hua 3
	2021
会议日期	JAN 10-15, 2021
会议地点	ELECTR NETWORK
关键词	Deep Learning Image Classification Loss Function Channel Attention
DOI	10.1109/ICPR48806.2021.9412069
页码	7601-7608
英文摘要	The loss function is a key component in deep learning models. A commonly used loss function for classification is the cross entropy loss, which is a simple yet effective application of information theory for classification problems. Based on this loss, many other loss functions have been proposed, e.g., by adding intra-class and inter-class constraints to enhance the discriminative ability of the learned features. However, these loss functions fail to consider the connections between the feature distribution and the model structure Aiming at addressing this problem, we propose a channel correlation loss (CC-Loss) that is able to constrain the specific relations between classes and channels as well as maintain the intra-class and the inter-class separability. CC-Loss uses a channel attention module to generate channel attention of features for each sample in the training stage. Next, an Euclidean distance matrix is calculated to make the channel attention vectors associated with the same class become identical and to increase the difference between different classes. Finally, we obtain a feature embedding with good intra-class compactness and inter-class separability. Experimental results show that two different backbone models trained with the proposed CC-Loss outperform the state-of-the-art loss functions on three image classification datasets.
会议录	2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)
会议录出版者	IEEE COMPUTER SOC
会议录出版地	LOS ALAMITOS
语种	英语
ISSN号	1051-4651
WOS研究方向	Computer Science ; Engineering ; Imaging Science & Photographic Technology
WOS记录号	WOS:000681331400001
内容类型	会议论文
源URL	[http://ir.lut.edu.cn/handle/2XXMBERH/150128]
专题	兰州理工大学
作者单位	1.Beijing Univ Posts & Telecommun, Beijing, Peoples R China; 2.Lanzhou Univ Technol, Lanzhou, Peoples R China; 3.Aalborg Univ, Aalborg, Denmark
推荐引用方式 GB/T 7714	Song, Zeyu,Chang, Dongliang,Ma, Zhanyu,et al. CC-LOSS: CHANNEL CORRELATION LOSS FOR IMAGE CLASSIFICATION[C]. 见:. ELECTR NETWORK. JAN 10-15, 2021.