Review — Colorful Image Colorization (Self-Supervised Learning)

Colorization as Pretext Task in Self-Supervised Learning, Outperforms Context Prediction & Context Encoders

Example Input Grayscale Photos and Output Colorizations

Outline

1. Colorful Image Colorization

Colorful Image Colorization: Network Architecture

1.1. L2 Loss is NOT Robust

1.2. Multinomial Classification Loss

Quantized ab color space with a grid size of 10

1.3. Class Probabilities to Point Estimates

e ect of temperature parameter T on the annealed-mean output

2. Colorization Results

Colorization results on 10k images in the ImageNet validation set

2.1. Perceptual realism (AMT)

2.2. Semantic Interpretability (VGG Classification)

2.3. Legacy Black and White Photos

Applying the proposed method to legacy black and white photos

2.4. More Examples

More Examples

3. Self-Supervised Learning Results

Left: ImageNet Linear Classification, Right: PASCAL Tests

3.1. ImageNet Classification

3.2. PASCAL Classification

3.3. PASCAL Detection

3.4. PASCAL Segmentation

By learning the colorization as pretext task without ground truth labels, useful features are learnt, which can be used for downstream tasks, such as image classification, detection, and segmentation.

PhD, Researcher. I share what I've learnt and done. :) My LinkedIn: https://www.linkedin.com/in/sh-tsang/, My Paper Reading List: https://bit.ly/33TDhxG