Fuzzy Overclustering: Semi-Supervised Classification of Fuzzy Labels with Overclustering and Inverse Cross-Entropy

by   Lars Schmarje, et al.

Deep learning has been successfully applied to many classification problems including underwater challenges. However, a long-standing issue with deep learning is the need for large and consistently labeled datasets. Although current approaches in semi-supervised learning can decrease the required amount of annotated data by a factor of 10 or even more, this line of research still uses distinct classes. For underwater classification, and uncurated real-world datasets in general, clean class boundaries can often not be given due to a limited information content in the images and transitional stages of the depicted objects. This leads to different experts having different opinions and thus producing fuzzy labels which could also be considered ambiguous or divergent. We propose a novel framework for handling semi-supervised classifications of such fuzzy labels. It is based on the idea of overclustering to detect substructures in these fuzzy labels. We propose a novel loss to improve the overclustering capability of our framework and show the benefit of overclustering for fuzzy labels. We show that our framework is superior to previous state-of-the-art semi-supervised methods when applied to real-world plankton data with fuzzy labels. Moreover, we acquire 5 to 10% more consistent predictions of substructures.


page 1

page 2

page 3

page 4


Beyond Cats and Dogs: Semi-supervised Classification of fuzzy labels with overclustering

A long-standing issue with deep learning is the need for large and consi...

S2C2 - An orthogonal method for Semi-Supervised Learning on fuzzy labels

Semi-Supervised Learning (SSL) can decrease the amount of required label...

Distributed Semi-supervised Fuzzy Regression with Interpolation Consistency Regularization

Recently, distributed semi-supervised learning (DSSL) algorithms have sh...

Life is not black and white – Combining Semi-Supervised Learning with fuzzy labels

The required amount of labeled data is one of the biggest issues in deep...

Semi-Supervised Visual Tracking of Marine Animals using Autonomous Underwater Vehicles

In-situ visual observations of marine organisms is crucial to developing...

An Ensemble Semi-Supervised Adaptive Resonance Theory Model with Explanation Capability for Pattern Classification

Most semi-supervised learning (SSL) models entail complex structures and...

Please sign up or login with your details

Forgot password? Click here to reset