A Baseline for Multi-Label Image Classification Using An Ensemble of Deep Convolutional Neural Networks
This work provides a standardized baseline for researchers in multi-label image classification, addressing incremental improvements by clarifying performance gains from complex techniques.
The paper tackles the problem of inconsistent comparisons and ambiguous advantages in multi-label image classification by establishing a strong baseline using basic deep convolutional neural networks with data augmentation and ensembles, achieving better performance than more complex methods on three benchmark datasets.
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.