Self-Supervised Learning


Introduced by Pathak et al. in Context Encoders: Feature Learning by Inpainting

Train a convolutional neural network to generate the contents of an arbitrary image region conditioned on its surroundings.

Source: Context Encoders: Feature Learning by Inpainting


Paper Code Results Date Stars


Task Papers Share
Image Inpainting 154 29.28%
Denoising 25 4.75%
Video Inpainting 23 4.37%
Image Generation 21 3.99%
Semantic Segmentation 20 3.80%
Super-Resolution 13 2.47%
Optical Flow Estimation 12 2.28%
Facial Inpainting 12 2.28%
Image Restoration 12 2.28%


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