Multi-layered Semantic Representation Network for Multi-label Image Classification

TL;DR

This paper introduces a Multi-layered Semantic Representation Network (MSRN) that enhances multi-label image classification by modeling local and global label semantics across multiple CNN layers, leading to improved performance.

Contribution

The paper proposes a novel MSRN that captures both local and global label semantics and learns semantic representations at multiple CNN layers using an attention mechanism.

Findings

MSRN outperforms state-of-the-art models on benchmark datasets.

Model effectively captures label correlations and multi-scale features.

Extensive experiments validate the approach's superiority.

Abstract

Multi-label image classification (MLIC) is a fundamental and practical task, which aims to assign multiple possible labels to an image. In recent years, many deep convolutional neural network (CNN) based approaches have been proposed which model label correlations to discover semantics of labels and learn semantic representations of images. This paper advances this research direction by improving both the modeling of label correlations and the learning of semantic representations. On the one hand, besides the local semantics of each label, we propose to further explore global semantics shared by multiple labels. On the other hand, existing approaches mainly learn the semantic representations at the last convolutional layer of a CNN. But it has been noted that the image representations of different layers of CNN capture different levels or scales of features and have different discriminative abilities. We thus propose to learn semantic representations at multiple convolutional layers. To this end, this paper designs a Multi-layered Semantic Representation Network (MSRN) which discovers both local and global semantics of labels through modeling label correlations and utilizes the label semantics to guide the semantic representations learning at multiple layers through an attention mechanism. Extensive experiments on four benchmark datasets including VOC 2007, COCO, NUS-WIDE, and Apparel show a competitive performance of the proposed MSRN against state-of-the-art models.