Review — RotNet: Unsupervised Representation Learning by Predicting Image Rotations

RotNet: Self-Supervised Learning by Predicting Image Rotations

The core intuition is that if someone is not aware of the concepts of the objects depicted in the images, he/she cannot recognize the rotation applied to the images

Outline

1. Image Rotation Prediction Framework

RotNet: Illustration of the self-supervised task
Attention maps generated by an AlexNet model trained (a) to recognize objects (supervised), and (b) to recognize image rotations (self-supervised).

2. Ablation Study & SOTA Comparison on CIFAR-10

2.1. Supervised Training on Each Layer on CIFAR

Evaluation of the unsupervised learned features by measuring the classification accuracy that they achieve when training a non-linear object classifier on top of them.

2.1. Number of Rotations

Exploring the quality of the self-supervised learned features w.r.t. the number of recognized rotations.

2.3. SOTA Comparison

Evaluation of unsupervised feature learning methods on CIFAR-10

3. Task Generalization on ImageNet, Places, & PASCAL VOC

3.1. ImageNet

Task Generalization: ImageNet top-1 classification with non-linear layers
Task Generalization: ImageNet top-1 classification with linear layers

3.2. Places

Task & Dataset Generalization: Places top-1 classification with linear layers

3.3. PASCAL VOC

Task & Dataset Generalization: PASCAL VOC 2007 classification and detection results, and PASCAL VOC 2012 segmentation results

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