CNN-RNN: A Unified Framework for Multi-label Image Classification

TL;DR

This paper introduces a CNN-RNN framework that models label dependencies explicitly for multi-label image classification, improving performance over existing methods by learning joint image-label embeddings end-to-end.

Contribution

The novel CNN-RNN architecture explicitly captures label dependencies and integrates image-label relevance in a unified, end-to-end trainable framework for multi-label classification.

Findings

Outperforms state-of-the-art models on benchmark datasets

Effectively models label dependencies and relevance

Achieves higher accuracy in multi-label classification

Abstract

While deep convolutional neural networks (CNNs) have shown a great success in single-label image classification, it is important to note that real world images generally contain multiple labels, which could correspond to different objects, scenes, actions and attributes in an image. Traditional approaches to multi-label image classification learn independent classifiers for each category and employ ranking or thresholding on the classification results. These techniques, although working well, fail to explicitly exploit the label dependencies in an image. In this paper, we utilize recurrent neural networks (RNNs) to address this problem. Combined with CNNs, the proposed CNN-RNN framework learns a joint image-label embedding to characterize the semantic label dependency as well as the image-label relevance, and it can be trained end-to-end from scratch to integrate both information in a unified framework. Experimental results on public benchmark datasets demonstrate that the proposed architecture achieves better performance than the state-of-the-art multi-label classification model