Unsupervised Deep Feature Transfer for Low Resolution Image Classification

Abstract

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.

arXiv comment4 pages, accepted to ICCV19 Workshop and Challenge on Real-World Recognition from Low-Quality Images and Videos

References in corpus (8)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• How transferable are features in deep neural networks?
• Learning Transferable Features with Deep Adaptation Networks
• Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
• Learning to Segment Object Candidates
• Learning Depth from Single Images with Deep Neural Network Embedding Focal Length
• Net2Net: Accelerating Learning via Knowledge Transfer
• Boosting Occluded Image Classification via Subspace Decomposition Based Estimation of Deep Features

Cited by in corpus (2)

• MDFN: Multi-Scale Deep Feature Learning Network for Object Detection
• Adaptively Denoising Proposal Collection for Weakly Supervised Object Localization