Fuzzy Overclustering: Semi-Supervised Classification of Fuzzy Labels with Overclustering and Inverse Cross-Entropy
arXiv:2110.06630 · doi:10.3390/s21196661
Abstract
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.
arXiv commentSource code: https://github.com/Emprime/FuzzyOverclustering Datasets: https://doi.org/10.5281/zenodo.5550918. arXiv admin note: substantial text overlap with arXiv:2012.01768
References in corpus (15)
- A Simple Framework for Contrastive Learning of Visual Representations
- FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
- Unsupervised Data Augmentation for Consistency Training
- Unsupervised Representation Learning by Predicting Image Rotations
- Temporal Ensembling for Semi-Supervised Learning
- Deep Label Distribution Learning with Label Ambiguity
- DivideMix: Learning with Noisy Labels as Semi-supervised Learning
- Deep Clustering for Unsupervised Learning of Visual Features
- Image Classification with Deep Learning in the Presence of Noisy Labels: A Survey
- A survey on Semi-, Self- and Unsupervised Learning for Image Classification
- A Realistic Fish-Habitat Dataset to Evaluate Algorithms for Underwater Visual Analysis
- Learning from Noisy Labels with Deep Neural Networks: A Survey
- Deep learning with self-supervision and uncertainty regularization to count fish in underwater images
- 2D and 3D Segmentation of uncertain local collagen fiber orientations in SHG microscopy
- FSL-BM: Fuzzy Supervised Learning with Binary Meta-Feature for Classification