DeepAI AI Chat
Log In Sign Up

Co-Representation Learning For Classification and Novel Class Detection via Deep Networks

by   Zhuoyi Wang, et al.

Deep Neural Network (DNN) has been largely demonstrated to be effective for closed-world classification problems where the total number of classes are known in advance. However, when the total number of classes that may occur during test time is unknown, DNNs notorious fail, i.e., DNN will make incorrect label prediction on instances from novel or unseen classes. This severely limits its utility in many real-world web applications, particularly when data occurs as a continuous stream. In this paper, we focus on addressing this key challenge by developing a two-channel DNN based co-representation learning framework that not only predicts instances from known classes, but also detects and adapts to the occurrence of novel class instances over time. Concretely, we propose a metric learning method using pairwise-constraint loss (PCL) function to learn a feature representation where intra-class compactness and inter-class separation is achieved. Moreover, we apply the temperature scaling scheme on the softmax function to replace traditional softmax output and design an open-world classifier. Our extensive empirical evaluation on benchmark datasets demonstrates the effectiveness of our framework compared to other competing techniques.


page 1

page 2

page 3

page 4


Adaptive Image Stream Classification via Convolutional Neural Network with Intrinsic Similarity Metrics

When performing data classification over a stream of continuously occurr...

Galaxy-X: A Novel Approach for Multi-class Classification in an Open Universe

Classification is a fundamental task in machine learning and artificial ...

Hyperspherical embedding for novel class classification

Deep learning models have become increasingly useful in many different i...

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

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

Detecting Novelties with Empty Classes

For open world applications, deep neural networks (DNNs) need to be awar...

Reducing Network Agnostophobia

Agnostophobia, the fear of the unknown, can be experienced by deep learn...

Backdoor Watermarking Deep Learning Classification Models With Deep Fidelity

Backdoor Watermarking is a promising paradigm to protect the copyright o...