DeepAI AI Chat
Log In Sign Up

S2OSC: A Holistic Semi-Supervised Approach for Open Set Classification

by   Yang Yang, et al.

Open set classification (OSC) tackles the problem of determining whether the data are in-class or out-of-class during inference, when only provided with a set of in-class examples at training time. Traditional OSC methods usually train discriminative or generative models with in-class data, then utilize the pre-trained models to classify test data directly. However, these methods always suffer from embedding confusion problem, i.e., partial out-of-class instances are mixed with in-class ones of similar semantics, making it difficult to classify. To solve this problem, we unify semi-supervised learning to develop a novel OSC algorithm, S2OSC, that incorporates out-of-class instances filtering and model re-training in a transductive manner. In detail, given a pool of newly coming test data, S2OSC firstly filters distinct out-of-class instances using the pre-trained model, and annotates super-class for them. Then, S2OSC trains a holistic classification model by combing in-class and out-of-class labeled data and remaining unlabeled test data in semi-supervised paradigm, which also integrates pre-trained model for knowledge distillation to further separate mixed instances. Despite its simplicity, the experimental results show that S2OSC achieves state-of-the-art performance across a variety of OSC tasks, including 85.4 pseudo-labels. We also demonstrate how S2OSC can be expanded to incremental OSC setting effectively with streaming data.


page 16

page 18


When Semi-Supervised Learning Meets Transfer Learning: Training Strategies, Models and Datasets

Semi-Supervised Learning (SSL) has been proved to be an effective way to...

Open-World Semi-Supervised Learning

Supervised and semi-supervised learning methods have been traditionally ...

Towards Semi-Supervised Learning for Deep Semantic Role Labeling

Neural models have shown several state-of-the-art performances on Semant...

Adaptive Negative Evidential Deep Learning for Open-set Semi-supervised Learning

Semi-supervised learning (SSL) methods assume that labeled data, unlabel...

Detecting Extrapolation with Local Ensembles

We present local ensembles, a method for detecting extrapolation at test...

Bayesian Optimization Meets Self-Distillation

Bayesian optimization (BO) has contributed greatly to improving model pe...