Unsupervised Embedding Quality Evaluation

05/26/2023
by   Anton Tsitsulin, et al.
0

Unsupervised learning has recently significantly gained in popularity, especially with deep learning-based approaches. Despite numerous successes and approaching supervised-level performance on a variety of academic benchmarks, it is still hard to train and evaluate SSL models in practice due to the unsupervised nature of the problem. Even with networks trained in a supervised fashion, it is often unclear whether they will perform well when transferred to another domain. Past works are generally limited to assessing the amount of information contained in embeddings, which is most relevant for self-supervised learning of deep neural networks. This works chooses to follow a different approach: can we quantify how easy it is to linearly separate the data in a stable way? We survey the literature and uncover three methods that could be potentially used for evaluating quality of representations. We also introduce one novel method based on recent advances in understanding the high-dimensional geometric structure self-supervised learning. We conduct extensive experiments and study the properties of these metrics and ones introduced in the previous work. Our results suggest that while there is no free lunch, there are metrics that can robustly estimate embedding quality in an unsupervised way.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/24/2020

Self-Supervised Learning for Large-Scale Unsupervised Image Clustering

Unsupervised learning has always been appealing to machine learning rese...
research
06/06/2021

Understand and Improve Contrastive Learning Methods for Visual Representation: A Review

Traditional supervised learning methods are hitting a bottleneck because...
research
03/27/2023

On the stepwise nature of self-supervised learning

We present a simple picture of the training process of self-supervised l...
research
10/29/2020

Combining Self-Training and Self-Supervised Learning for Unsupervised Disfluency Detection

Most existing approaches to disfluency detection heavily rely on human-a...
research
06/09/2022

Rethinking 360° Image Visual Attention Modelling with Unsupervised Learning

Despite the success of self-supervised representation learning on plana...
research
04/08/2022

Self-supervised Speaker Diarization

Over the last few years, deep learning has grown in popularity for speak...
research
12/28/2021

To Supervise or Not: How to Effectively Learn Wireless Interference Management Models?

Machine learning has become successful in solving wireless interference ...

Please sign up or login with your details

Forgot password? Click here to reset