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

Source: [Fine-to-coarse Knowledge Transfer For Low-Res Image Classification](<https://www.sota2.com/research/paper/68fa627b1e209131ce9f97d6>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:20:33.540Z

Authors: Xingchao Peng, Judy Hoffman, Stella X. Yu, Kate Saenko

Published: 2016-05-21T20:08:53.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1605.06695>)

[PDF](<https://arxiv.org/pdf/1605.06695.pdf>)