Review — Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles

Solving Jigsaw Puzzles as Pretext Task for Self-Supervised Learning

Learning image representations by solving Jigsaw puzzles. (a): The image from which the tiles (marked with green lines) are extracted. (b): A puzzle obtained by shuffling the tiles. (c): determining the relative position (the relative location between the central tile and the top-left and top-middle tiles is ambiguous.)

Outline

1. Feature Learning by Solving Jigsaw Puzzles

1.1. Conceptual Idea

Most of the shape of these 2 pairs of images is the same

1.2. Naïve Stacked Patches NOT Working

2. Context Free Network (CFN): Network Architecture

Context Free Network (CFN): Network Architecture

2.1. Framework

2.2. Training

2.3. Avoid Shortcuts

3. Experimental Results

3.1. ImageNet

3.2. PASCAL VOC

Results on PASCAL VOC 2007 Detection and Classification

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