Colorization is a self-supervision approach that relies on colorization as the pretext task in order to learn image representations.
Source: Colorful Image ColorizationPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Colorization | 182 | 46.91% |
Decoder | 10 | 2.58% |
Super-Resolution | 10 | 2.58% |
Translation | 9 | 2.32% |
Semantic correspondence | 9 | 2.32% |
Semantic Segmentation | 9 | 2.32% |
Image Generation | 7 | 1.80% |
Denoising | 7 | 1.80% |
Object Detection | 6 | 1.55% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |