# Image Enhanced Rotation Prediction for Self-Supervised Learning

arXiv: https://arxiv.org/abs/1912.11603 · HTML: https://mlsanity.com/paper/1912.11603/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Dec 2019.

## Built on by (most cited first, 7 of 7)

- [Equivariant Contrastive Learning](https://mlsanity.com/paper/2111.00899/) (2021)
- [Self-Supervised Learning for Text Recognition: A Critical Survey](https://mlsanity.com/paper/2407.19889/) (2024)
- [Spatial Context-based Self-Supervised Learning for Handwritten Text Recognition](https://mlsanity.com/paper/2404.11585/) (2024)
- [Self-Supervised Pretext Tasks for Alzheimer's Disease Classification using 3D Convolutional Neural Networks on Large-Scale Synthetic Neuroimaging Dataset](https://mlsanity.com/paper/2406.14210/) (2024)
- [WSSL: Weighted Self-supervised Learning Framework For Image-inpainting](https://mlsanity.com/paper/2211.13856/) (2022)
- [Self-Supervised Learning from Non-Object Centric Images with a Geometric Transformation Sensitive Architecture](https://mlsanity.com/paper/2304.08014/) (2023)
- [Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training?](https://mlsanity.com/paper/2607.13192/) (2026)

## Abstract (arXiv)

The rotation prediction (Rotation) is a simple pretext-task for self-supervised learning (SSL), where models learn useful representations for target vision tasks by solving pretext-tasks. Although Rotation captures information of object shapes, it hardly captures information of textures. To tackle this problem, we introduce a novel pretext-task called image enhanced rotation prediction (IE-Rot) for SSL. IE-Rot simultaneously solves Rotation and another pretext-task based on image enhancement (e.g., sharpening and solarizing) while maintaining simplicity. Through the simultaneous prediction of rotation and image enhancement, models learn representations to capture the information of not only object shapes but also textures. Our experimental results show that IE-Rot models outperform Rotation on various standard benchmarks including ImageNet classification, PASCAL-VOC detection, and COCO detection/segmentation.