# Benefiting from Multitask Learning to Improve Single Image Super-Resolution

arXiv: https://arxiv.org/abs/1907.12488 · HTML: https://mlsanity.com/paper/1907.12488/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jul 2019.

## Built on by (most cited first, 5 of 5)

- [Hard Exudate Segmentation Supplemented by Super-Resolution with Multi-scale Attention Fusion Module](https://mlsanity.com/paper/2211.09404/) (2022)
- [Self-Taught Semi-Supervised Anomaly Detection on Upper Limb X-rays](https://mlsanity.com/paper/2102.09895/) (2021)
- [Test-Time Adaptation for Super-Resolution: You Only Need to Overfit on a Few More Images](https://mlsanity.com/paper/2104.02663/) (2021)
- [Task-driven single-image super-resolution reconstruction of document scans](https://mlsanity.com/paper/2407.08993/) (2024)
- [Task-driven real-world super-resolution of document scans](https://mlsanity.com/paper/2506.06953/) (2025)

## Abstract (arXiv)

Despite significant progress toward super resolving more realistic images by deeper convolutional neural networks (CNNs), reconstructing fine and natural textures still remains a challenging problem. Recent works on single image super resolution (SISR) are mostly based on optimizing pixel and content wise similarity between recovered and high-resolution (HR) images and do not benefit from recognizability of semantic classes. In this paper, we introduce a novel approach using categorical information to tackle the SISR problem; we present a decoder architecture able to extract and use semantic information to super-resolve a given image by using multitask learning, simultaneously for image super-resolution and semantic segmentation. To explore categorical information during training, the proposed decoder only employs one shared deep network for two task-specific output layers. At run-time only layers resulting HR image are used and no segmentation label is required. Extensive perceptual experiments and a user study on images randomly selected from COCO-Stuff dataset demonstrate the effectiveness of our proposed method and it outperforms the state-of-the-art methods.