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

by   Lars Schmarje, et al.

Semi-Supervised Learning (SSL) can decrease the amount of required labeled image data and thus the cost for deep learning. Most SSL methods only consider a clear distinction between classes but in many real-world datasets, this clear distinction is not given due to intra- or interobserver variability. This variability can lead to different annotations per image. Thus many images have ambiguous annotations and their label needs to be considered "fuzzy". This fuzziness of labels must be addressed as it will limit the performance of Semi-Supervised Learning (SSL) and deep learning in general. We propose Semi-Supervised Classification Clustering (S2C2) which can extend many deep SSL algorithms. S2C2 can estimate the fuzziness of a label and applies SSL as a classification to certainly labeled data while creating distinct clusters for images with similar but fuzzy labels. We show that S2C2 results in median 7.4 better F1-score for classifications and 5.4 across multiple SSL algorithms and datasets while being more interpretable due to the fuzziness estimation of our method. Overall, a combination of Semi-Supervised Learning with our method S2C2 leads to better handling of the fuzziness of labels and thus real-world datasets.


page 8

page 12


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

Deep learning has been successfully applied to many classification probl...

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...

RVSL: Robust Vehicle Similarity Learning in Real Hazy Scenes Based on Semi-supervised Learning

Recently, vehicle similarity learning, also called re-identification (Re...

L^γ-PageRank for Semi-Supervised Learning

PageRank for Semi-Supervised Learning has shown to leverage data structu...

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...

Semi-Supervised Audio Classification with Partially Labeled Data

Audio classification has seen great progress with the increasing availab...

Please sign up or login with your details

Forgot password? Click here to reset