.png){kind=icon}
.png){kind=icon}
Return
Semantic representation and dependency learning for multi-label image recognition
.png){kind=icon}
OA
AI
DOI：10.1016/j.neucom.2023.01.018.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Recently many multi-label image recognition (MLR) works have made significant progress by introducing pre-trained object detection models to generate lots of proposals or utilizing statistical label co-occurrence to enhance the correlation among different categories. However, these works have some lim-itations: (1) the effectiveness of the network significantly depends on pre-trained object detection mod-els that bring expensive and unaffordable computation; (2) the network performance degrades when there exist occasional co-occurrence objects in images, especially for the rare categories. To address these problems, we propose a novel and effective semantic representation and dependency learning (SRDL) framework to learn category-specific semantic representation for each category and capture semantic dependency among all categories. Specifically, we design a category-specific attentional regions (CAR) module to generate channel/spatial-wise attention matrices to guide the model to focus on semantic -aware regions. We also design an object erasing (OE) module to implicitly learn semantic dependency among categories by erasing semantic-aware regions to regularize the network training. Extensive exper-iments and comparisons on two popular MLR benchmark datasets (i.e., MS-COCO and Pascal VOC 2007) demonstrate the effectiveness of the proposed framework over current state-of-the-art algorithms.(c) 2023 Elsevier B.V. All rights reserved.
Keywords:
Multi -label image recognition
Representation learning
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W