.png){kind=icon}
Return
Cross-View Representation Learning: A Superior ContextIB Method for Logo Classification
.png){kind=icon}
PRE
AI
DOI：10.1109/LSP.2024.3356419.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Logo classification systems have become increasingly important in various industries for tasks, such as infringement detection and industrial production. However, challenges still exist in logo classification due to real-world image background interference, the high similarity between classes, labeling difficulties, and the insufficient representation of occlusion in single-view logos. Many existing algorithms fail to consider the data characteristics and the intrinsic information of multiple views, which limits their performance. To overcome these limitations, we developed a novel Cross-View Information Awareness Network (CVIA-Net) for logo classification. To differentiate between similar logo categories, the CVIA-Net novel learns context-shared features of the same category via a self-supervised way without labeled, which solves the problem of insufficient features due to occlusion. For single-view images, CVIA-Net establishes a bottleneck representation to address background interference. Extensive experiments on three datasets demonstrate that it outperforms state-of-the-art methods. The method is expected to advance the development of cross-view representation learning.
Keywords:
Feature extraction
Representation learning
Image coding
Data mining
Task analysis
Interference
Classification algorithms
Artificial intelligence
computer vision
informat- ion bottleneck
logo classification
representation learning
Journal
IF:
9.6
Papers:
1.1W
Citations:
1.7W
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSave
ShareSaveMicrostructure of Low-fat Cheddar Cheese Containing Varying Concentrations of Sucrose Polyesters
PREAI
ShareSaveShareSave
View more