Article
Version 1
Preserved in Portico This version is not peer-reviewed
Long-tailed Image Classification Method Based on Enhanced Contrastive Visual-language
Version 1
: Received: 22 June 2023 / Approved: 23 June 2023 / Online: 23 June 2023 (12:17:21 CEST)
A peer-reviewed article of this Preprint also exists.
Song, Y.; Li, M.; Wang, B. A Long-Tailed Image Classification Method Based on Enhanced Contrastive Visual Language. Sensors 2023, 23, 6694. Song, Y.; Li, M.; Wang, B. A Long-Tailed Image Classification Method Based on Enhanced Contrastive Visual Language. Sensors 2023, 23, 6694.
Abstract
To solve the problem that the common long-tailed classification method does not use the semantic features of the original label text of the image, and the difference between the classification accuracy of most classes and minority classes is large, the long-tailed image classification method based on enhanced contrast visual language trains the head class and tail class samples separately, uses text image to pre-train the information, and uses enhanced momentum contrast loss function and RandAugment enhancement to improve the learning of tail class samples. On the ImageNet-LT long-tailed dataset, the enhanced contrastive visual-language based long-tailed image classification method has improved all class accuracy, tail class accuracy, middle class accuracy, and F1 values by 3.4%, 7.6%, 3.5%, and 11.2%, respectively, compared to the BALLAD method. The difference in accuracy between the head class and tail class is reduced by 1.6% compared to the BALLAD method. The results of three comparative experiments indicate that the long-tailed image classification method based on enhanced contrastive visual-language has improved the performance of tail classes and reduced the accuracy difference between majority and minority classes.
Keywords
long-tailed image classification; contrastive learning; data augmentation
Subject
Computer Science and Mathematics, Computer Vision and Graphics
Copyright: This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Comments (0)
We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.
Leave a public commentSend a private comment to the author(s)
* All users must log in before leaving a comment