DeepAI AI Chat
Log In Sign Up

MetaMax: Improved Open-Set Deep Neural Networks via Weibull Calibration

by   Zongyao Lyu, et al.
The University of Texas at Arlington

Open-set recognition refers to the problem in which classes that were not seen during training appear at inference time. This requires the ability to identify instances of novel classes while maintaining discriminative capability for closed-set classification. OpenMax was the first deep neural network-based approach to address open-set recognition by calibrating the predictive scores of a standard closed-set classification network. In this paper we present MetaMax, a more effective post-processing technique that improves upon contemporary methods by directly modeling class activation vectors. MetaMax removes the need for computing class mean activation vectors (MAVs) and distances between a query image and a class MAV as required in OpenMax. Experimental results show that MetaMax outperforms OpenMax and is comparable in performance to other state-of-the-art approaches.


Learning a Neural-network-based Representation for Open Set Recognition

Open set recognition problems exist in many domains. For example in secu...

Open-Set Recognition Using Intra-Class Splitting

This paper proposes a method to use deep neural networks as end-to-end o...

One-vs-Rest Network-based Deep Probability Model for Open Set Recognition

Unknown examples that are unseen during training often appear in real-wo...

Evaluation of Various Open-Set Medical Imaging Tasks with Deep Neural Networks

The current generation of deep neural networks has achieved close-to-hum...

Evaluating Uncertainty Calibration for Open-Set Recognition

Despite achieving enormous success in predictive accuracy for visual cla...

Deep Compact Polyhedral Conic Classifier for Open and Closed Set Recognition

In this paper, we propose a new deep neural network classifier that simu...

DeepStreamCE: A Streaming Approach to Concept Evolution Detection in Deep Neural Networks

Deep neural networks have experimentally demonstrated superior performan...