Rethinking Recurrent Neural Networks and Other Improvements for Image Classification
This work addresses image recognition for computer vision applications, but it is incremental as it builds on existing methods with hybrid improvements.
The authors tackled image classification by integrating RNNs as additional layers and using end-to-end multimodel ensembles, achieving state-of-the-art results on datasets like SVHN (0.99), Cifar-100 (0.9027), Cifar-10 (0.9852), and setting a new record on Surrey (0.949).
Over the long history of machine learning, which dates back several decades, recurrent neural networks (RNNs) have been used mainly for sequential data and time series and generally with 1D information. Even in some rare studies on 2D images, these networks are used merely to learn and generate data sequentially rather than for image recognition tasks. In this study, we propose integrating an RNN as an additional layer when designing image recognition models. We also develop end-to-end multimodel ensembles that produce expert predictions using several models. In addition, we extend the training strategy so that our model performs comparably to leading models and can even match the state-of-the-art models on several challenging datasets (e.g., SVHN (0.99), Cifar-100 (0.9027) and Cifar-10 (0.9852)). Moreover, our model sets a new record on the Surrey dataset (0.949). The source code of the methods provided in this article is available at https://github.com/leonlha/e2e-3m and http://nguyenhuuphong.me.