Self-Supervised Learning

Colorization

Introduced by Zhang et al. in Colorful Image Colorization

Colorization is a self-supervision approach that relies on colorization as the pretext task in order to learn image representations.

Source: Colorful Image Colorization

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Colorization 176 47.83%
Super-Resolution 10 2.72%
Semantic correspondence 9 2.45%
Semantic Segmentation 9 2.45%
Translation 8 2.17%
Denoising 7 1.90%
Object Detection 6 1.63%
Line Art Colorization 6 1.63%
Image Generation 6 1.63%

Components


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories