# Exploring Simple and Transferable Recognition-Aware Image Processing

arXiv: https://arxiv.org/abs/1910.09185 · HTML: https://mlsanity.com/paper/1910.09185/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Oct 2019.

## Built on by (most cited first, 6 of 6)

- [MWFormer: Multi-Weather Image Restoration Using Degradation-Aware Transformers](https://mlsanity.com/paper/2411.17226/) (2024)
- [Data Poisoning in Deep Learning: A Survey](https://mlsanity.com/paper/2503.22759/) (2025)
- [Beyond Image Super-Resolution for Image Recognition with Task-Driven Perceptual Loss](https://mlsanity.com/paper/2404.01692/) (2024)
- [Image Quality-aware Diagnosis via Meta-knowledge Co-embedding](https://mlsanity.com/paper/2303.15038/) (2023)
- [Efficient Deweather Mixture-of-Experts with Uncertainty-aware Feature-wise Linear Modulation](https://mlsanity.com/paper/2312.16610/) (2023)
- [Generalized Task-Driven Medical Image Quality Enhancement with Gradient Promotion](https://mlsanity.com/paper/2501.01114/) (2025)

## Abstract (arXiv)

Recent progress in image recognition has stimulated the deployment of vision systems at an unprecedented scale. As a result, visual data are now often consumed not only by humans but also by machines. Existing image processing methods only optimize for better human perception, yet the resulting images may not be accurately recognized by machines. This can be undesirable, e.g., the images can be improperly handled by search engines or recommendation systems. In this work, we examine simple approaches to improve machine recognition of processed images: optimizing the recognition loss directly on the image processing network or through an intermediate input transformation model. Interestingly, the processing model's ability to enhance recognition quality can transfer when evaluated on models of different architectures, recognized categories, tasks and training datasets. This makes the methods applicable even when we do not have the knowledge of future recognition models, e.g., when uploading processed images to the Internet. We conduct experiments on multiple image processing tasks paired with ImageNet classification and PASCAL VOC detection as recognition tasks. With these simple yet effective methods, substantial accuracy gain can be achieved with strong transferability and minimal image quality loss. Through a user study we further show that the accuracy gain can transfer to a black-box cloud model. Finally, we try to explain this transferability phenomenon by demonstrating the similarities of different models' decision boundaries. Code is available at https://github.com/liuzhuang13/Transferable_RA .