Image Enhanced Rotation Prediction for Self-Supervised Learning
| Autor: | Shin'ya Yamaguchi, Tetsuya Shioda, Sekitoshi Kanai, Shoichiro Takeda |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Self supervised learning business.industry Computer science Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Machine Learning (stat.ML) Pattern recognition Sharpening Object (computer science) Machine Learning (cs.LG) Image (mathematics) Statistics - Machine Learning Simple (abstract algebra) Simplicity (photography) Segmentation Artificial intelligence business Rotation (mathematics) |
| Zdroj: | 2021 IEEE International Conference on Image Processing (ICIP). |
| DOI: | 10.1109/icip42928.2021.9506132 |
| Popis: | 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. Accepted to IEEE ICIP 2021. The title has been changed from "Multiple Pretext-Task for Self-Supervised Learning via Mixing Multiple Image Transformations" |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|