Unsupervised Deep Feature Transfer for Low Resolution Image Classification
This addresses the problem of image classification under low-resolution conditions for computer vision applications, representing an incremental improvement with a plug-in module.
The paper tackles low-resolution image classification by proposing an unsupervised deep feature transfer algorithm that transfers distinguishing features from high-resolution to low-resolution feature spaces, achieving significant improvements over baseline feature extraction on the VOC2007 test set.
In this paper, we propose a simple while effective unsupervised deep feature transfer algorithm for low resolution image classification. No fine-tuning on convenet filters is required in our method. We use pre-trained convenet to extract features for both high- and low-resolution images, and then feed them into a two-layer feature transfer network for knowledge transfer. A SVM classifier is learned directly using these transferred low resolution features. Our network can be embedded into the state-of-the-art deep neural networks as a plug-in feature enhancement module. It preserves data structures in feature space for high resolution images, and transfers the distinguishing features from a well-structured source domain (high resolution features space) to a not well-organized target domain (low resolution features space). Extensive experiments on VOC2007 test set show that the proposed method achieves significant improvements over the baseline of using feature extraction.