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

arXiv: https://arxiv.org/abs/1605.06695 · HTML: https://mlsanity.com/paper/1605.06695/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 May 2016.

## Built on by (most cited first, 11 of 11)

- [No More Strided Convolutions or Pooling: A New CNN Building Block for Low-Resolution Images and Small Objects](https://mlsanity.com/paper/2208.03641/) (2022)
- [Deep Rival Penalized Competitive Learning for Low-resolution Face Recognition](https://mlsanity.com/paper/2108.01286/) (2021)
- [Resolution-Invariant Image Classification based on Fourier Neural Operators](https://mlsanity.com/paper/2304.01227/) (2023)
- [How Quality Affects Deep Neural Networks in Fine-Grained Image Classification](https://mlsanity.com/paper/2405.05742/) (2024)
- [Learning degraded image classification with restoration data fidelity](https://mlsanity.com/paper/2101.09606/) (2021)
- [Automated System for Ship Detection from Medium Resolution Satellite Optical Imagery](https://mlsanity.com/paper/2104.13923/) (2021)
- [Teacher Network Calibration Improves Cross-Quality Knowledge Distillation](https://mlsanity.com/paper/2304.07593/) (2023)
- [Cross-Domain Knowledge Distillation for Low-Resolution Human Pose Estimation](https://mlsanity.com/paper/2405.11448/) (2024)
- [Focus on Low-Resolution Information: Multi-Granular Information-Lossless Model for Low-Resolution Human Pose Estimation](https://mlsanity.com/paper/2405.12247/) (2024)
- [CMD: Constraining Multimodal Distribution for Domain Adaptation in Stereo Matching](https://mlsanity.com/paper/2504.21302/) (2025)
- [On What We Can Learn from Low-Resolution Data](https://mlsanity.com/paper/2605.12168/) (2026)

## Abstract (arXiv)

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.