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.

本文提出了一种简单而有效的无监督深度特征传递算法，用于低分辨率图像分类，无需 fine-tuning。首先，我们使用预先训练的 convenet 提取高分辨率和低分辨率图像的特征，然后将它们馈送到两层特征转移网络以进行知识转移。接着，我们直接使用这些传递的低分辨率特征学习 SVM 分类器。该网络可以作为插件特征增强模块嵌入到最新的深度神经网络中，以保持高分辨率图像特征空间中的数据结构，并将良好结构的源域 (高分辨率特征空间) 的区分特征传递到不良组织的目标域 (低分辨率特征空间) 上。通过对 VOC2007 测试集的大量实验证明，所提出的方法比仅使用特征提取的基线方法实现了显著的性能改善。