ResFeats: Residual Network Based Features for Image Classification
This work addresses image classification problems for researchers and practitioners by offering an incremental improvement over existing CNN features.
The paper tackled image classification by proposing ResFeats, features extracted from pre-trained deep residual networks, and showed they consistently outperform CNN features on object, scene, and coral classification tasks, achieving state-of-the-art accuracies on Caltech-101, Caltech-256, and MLC datasets with significant improvement on MIT-67.
Deep residual networks have recently emerged as the state-of-the-art architecture in image segmentation and object detection. In this paper, we propose new image features (called ResFeats) extracted from the last convolutional layer of deep residual networks pre-trained on ImageNet. We propose to use ResFeats for diverse image classification tasks namely, object classification, scene classification and coral classification and show that ResFeats consistently perform better than their CNN counterparts on these classification tasks. Since the ResFeats are large feature vectors, we propose to use PCA for dimensionality reduction. Experimental results are provided to show the effectiveness of ResFeats with state-of-the-art classification accuracies on Caltech-101, Caltech-256 and MLC datasets and a significant performance improvement on MIT-67 dataset compared to the widely used CNN features.