RotNet is a self-supervision approach that relies on predicting image rotations as the pretext task in order to learn image representations.
Source: RotNet: Fast and Scalable Estimation of Stellar Rotation Periods Using Convolutional Neural NetworksPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Domain Adaptation | 1 | 10.00% |
Image Classification | 1 | 10.00% |
Image Retrieval | 1 | 10.00% |
Retrieval | 1 | 10.00% |
Self-Supervised Learning | 1 | 10.00% |
Semantic Segmentation | 1 | 10.00% |
Sketch-Based Image Retrieval | 1 | 10.00% |
Open Set Learning | 1 | 10.00% |
Feature Engineering | 1 | 10.00% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |