Semi-Supervised Class Discovery
arXiv:2002.03480
Abstract
One promising approach to dealing with datapoints that are outside of the initial training distribution (OOD) is to create new classes that capture similarities in the datapoints previously rejected as uncategorizable. Systems that generate labels can be deployed against an arbitrary amount of data, discovering classification schemes that through training create a higher quality representation of data. We introduce the Dataset Reconstruction Accuracy, a new and important measure of the effectiveness of a model's ability to create labels. We introduce benchmarks against this Dataset Reconstruction metric. We apply a new heuristic, class learnability, for deciding whether a class is worthy of addition to the training dataset. We show that our class discovery system can be successfully applied to vision and language, and we demonstrate the value of semi-supervised learning in automatically discovering novel classes.
References in corpus (15)
- Scikit-learn: Machine Learning in Python
- Distributed Representations of Words and Phrases and their Compositionality
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
- Understanding deep learning requires rethinking generalization
- A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
- Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift
- Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks
- MixMatch: A Holistic Approach to Semi-Supervised Learning
- Deep Clustering for Unsupervised Learning of Visual Features
- Recovering the number of clusters in data sets with noise features using feature rescaling factors
- Continual Unsupervised Representation Learning
- Unseen Class Discovery in Open-world Classification
- AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence
- Deep Metric Learning via Facility Location