Geek Culture
Published in

Geek Culture

Review — Exemplar-CNN: Discriminative Unsupervised Feature Learning with Convolutional Neural Networks (Self-Supervised Learning)

Exemplar-CNN: Trained on Unlabeled Data Using Surrogate Class by Data Transformation

Surrogate classes are generated by data transformation using unlabeled data


1. Creating Surrogate Training Data & Learning Algorithm

1.1. Creating Surrogate Training Data

Exemplary patches sampled from the STL unlabeled dataset which are later augmented by various transformations to obtain surrogate data for the CNN training.
Several random transformations applied to one of the patches extracted from the STL unlabeled dataset. The original (’seed’) patch is in the top left corner.

1.2. Learning Algorithm

2. CNN Architectures & Experimental Setup

2.1. Unlabeled Dataset for Surrogate Class

2.2. Two CNNs

2.3. Pooled Features for Linear SVM

3. Experimental Results

3.1. SOTA Comparison

Classification accuracies on several datasets

3.2. Number of Surrogate Classes

Influence of the number of surrogate training classes

3.3. Number of Samples per Surrogate Class

Classification performance on STL for different numbers of samples per class

3.4. Types of Transformations

Influence of removing groups of transformations during generation of the surrogate training data.


Self-Supervised Learning



A new tech publication by Start it up (

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store