English

Fine-to-coarse Knowledge Transfer For Low-Res Image Classification

Computer Vision and Pattern Recognition 2016-05-24 v1

Abstract

We address the difficult problem of distinguishing fine-grained object categories in low resolution images. Wepropose a simple an effective deep learning approach that transfers fine-grained knowledge gained from high resolution training data to the coarse low-resolution test scenario. Such fine-to-coarse knowledge transfer has many real world applications, such as identifying objects in surveillance photos or satellite images where the image resolution at the test time is very low but plenty of high resolution photos of similar objects are available. Our extensive experiments on two standard benchmark datasets containing fine-grained car models and bird species demonstrate that our approach can effectively transfer fine-detail knowledge to coarse-detail imagery.

Keywords

Cite

@article{arxiv.1605.06695,
  title  = {Fine-to-coarse Knowledge Transfer For Low-Res Image Classification},
  author = {Xingchao Peng and Judy Hoffman and Stella X. Yu and Kate Saenko},
  journal= {arXiv preprint arXiv:1605.06695},
  year   = {2016}
}

Comments

5 pages, accepted by ICIP 2016

R2 v1 2026-06-22T14:06:28.489Z