A Baseline for Multi-Label Image Classification Using An Ensemble of Deep Convolutional Neural Networks

TL;DR

This paper establishes a strong baseline for multi-label image classification by thoroughly investigating mainstream deep CNN architectures and demonstrating that simple ensemble methods with proper data augmentation outperform more complex models on benchmark datasets.

Contribution

It provides a comprehensive baseline analysis for multi-label classification, highlighting the effectiveness of simple ensembles and data augmentation over complex architectures.

Findings

Ensembles with basic CNNs outperform complex models.

Proper data augmentation improves classification performance.

Baseline results facilitate fair comparison in future research.

Abstract

Recent studies on multi-label image classification have focused on designing more complex architectures of deep neural networks such as the use of attention mechanisms and region proposal networks. Although performance gains have been reported, the backbone deep models of the proposed approaches and the evaluation metrics employed in different works vary, making it difficult to compare each fairly. Moreover, due to the lack of properly investigated baselines, the advantage introduced by the proposed techniques are often ambiguous. To address these issues, we make a thorough investigation of the mainstream deep convolutional neural network architectures for multi-label image classification and present a strong baseline. With the use of proper data augmentation techniques and model ensembles, the basic deep architectures can achieve better performance than many existing more complex ones on three benchmark datasets, providing great insight for the future studies on multi-label image classification.