Generative OpenMax for Multi-Class Open Set Classification

2017/07/24 by Zongyuan Ge, Ge, ZongYuan, Sergey Demyanov +5 · 15 citations
Computer Science · Engineering · #Computer Vision and Pattern Recognition (cs.CV) #Digital Imaging for Blood Diseases #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Image Processing Techniques and Applications

paper · pdf · doi:10.48550/arxiv.1707.07418

openalex publication_date 2017/07/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We present a conceptually new and flexible method for multi-class open set classification. Unlike previous methods where unknown classes are inferred with respect to the feature or decision distance to the known classes, our approach is able to provide explicit modelling and decision score for unknown classes. The proposed method, called Gener- ative OpenMax (G-OpenMax), extends OpenMax by employing generative adversarial networks (GANs) for novel category image synthesis. We validate the proposed method on two datasets of handwritten digits and characters, resulting in superior results over previous deep learning based method OpenMax Moreover, G-OpenMax provides a way to visualize samples representing the unknown classes from open space. Our simple and effective approach could serve as a new direction to tackle the challenging multi-class open set classification problem.

Citations

• Improved Techniques for Training GANs
• Conditional Image Synthesis With Auxiliary Classifier GANs
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

Cited by

• Coarse-to-Fine Open-Set Graph Node Classification with Large Language Models
• Hierarchical Attention for Sparse Volumetric Anomaly Detection in Subclinical Keratoconus
• Drainage: A Unifying Framework for Addressing Class Uncertainty
• Open-Set Domain Adaptation Under Background Distribution Shift: Challenges and A Provably Efficient Solution
• UCDSC: Open Set UnCertainty aware Deep Simplex Classifier for Medical Image Datasets
• Open Set Recognition with Conditional Probabilistic Generative Models
• Information Theory in Open-world Machine Learning Foundations, Frameworks, and Future Direction
• Conformal Inference for Open-Set and Imbalanced Classification
• Training-Free Label Space Alignment for Universal Domain Adaptation
• Evolving from Unknown to Known: Retentive Angular Representation Learning for Incremental Open Set Recognition
• Empirical Evidences for the Effects of Feature Diversity in Open Set Recognition and Continual Learning
• Multi-Domain Supervised Contrastive Learning for UAV Radio-Frequency Open-Set Recognition
• Learning without Seeing nor Knowing: Towards Open Zero-Shot Learning
• Few-Shot Open-Set Recognition using Meta-Learning
• Handling Out-of-Distribution Data: A Survey

Related

• OpenGAN: Open Set Generative Adversarial Networks
• MetaMax: Improved Open-Set Deep Neural Networks via Weibull Calibration
• Towards Open Set Deep Networks
• Deep CNN-based Multi-task Learning for Open-Set Recognition
• OpenGCD: Assisting Open World Recognition with Generalized Category Discovery