A Baseline for Multi-Label Image Classification Using an Ensemble of Deep Convolutional Neural Networks
Authors:
- 1 September 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 644-648
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 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.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- Improving Pairwise Ranking for Multi-label Image Classification2017
- Learning Spatial Regularization with Image-Level Supervisions for Multi-label Image Classification2017
- Beyond Object Proposals: Random Crop Pooling for Multi-Label Image RecognitionIEEE Transactions on Image Processing, 2016
- Deep Residual Learning for Image Recognition2016
- CNN-RNN: A Unified Framework for Multi-label Image Classification2016
- Fast Zero-Shot Image Tagging2016
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- A Hybrid Probabilistic Model for Unified Collaborative and Content-Based Image TaggingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- NUS-WIDE2009