TR2019-127

Unsupervised Deep Feature Transfer for Low Resolution Image Classification


    •  Zhang, Z., Wu, Y., Wang, G., "Unsupervised Deep Feature Transfer for Low Resolution Image Classification", IEEE International Conference on Computer Vision Workshops (ICCV), DOI: 10.1109/ICCVW.2019.00136, October 2019, pp. 1065-1069.
      BibTeX TR2019-127 PDF
      • @inproceedings{Zhang2019oct,
      • author = {Zhang, Ziming and Wu, Yuanwei and Wang, Guanghui},
      • title = {Unsupervised Deep Feature Transfer for Low Resolution Image Classification},
      • booktitle = {IEEE International Conference on Computer Vision Workshops (ICCV)},
      • year = 2019,
      • pages = {1065--1069},
      • month = oct,
      • doi = {10.1109/ICCVW.2019.00136},
      • url = {https://www.merl.com/publications/TR2019-127}
      • }
  • Research Areas:

    Artificial Intelligence, Computer Vision, Machine Learning

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 wellstructured 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.