Wang, Q. and Ning, J. and Breckon, T.P. (2019) 'A baseline for multi-label image classification using an ensemble of deep convolutional neural networks.', in 2019 IEEE International Conference on Image Processing (ICIP) ; proceedings. Piscataway, NJ: IEEE, pp. 644-648.
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 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.
|Item Type:||Book chapter|
|Full text:||(AM) Accepted Manuscript|
Download PDF (268Kb)
|Publisher Web site:||https://doi.org/10.1109/ICIP.2019.8803793|
|Publisher statement:||© 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.|
|Date accepted:||30 April 2019|
|Date deposited:||05 June 2019|
|Date of first online publication:||September 2019|
|Date first made open access:||12 November 2019|
Save or Share this output
|Look up in GoogleScholar|