DeepAI AI Chat
Log In Sign Up

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

by   Yang Gao, et al.
The University of Texas at Dallas

When performing data classification over a stream of continuously occurring instances, a key challenge is to develop an open-world classifier that anticipates instances from an unknown class. Studies addressing this problem, typically called novel class detection, have considered classification methods that reactively adapt to such changes along the stream. Importantly, they rely on the property of cohesion and separation among instances in feature space. Instances belonging to the same class are assumed to be closer to each other (cohesion) than those belonging to different classes (separation). Unfortunately, this assumption may not have large support when dealing with high dimensional data such as images. In this paper, we address this key challenge by proposing a semisupervised multi-task learning framework called CSIM which aims to intrinsically search for a latent space suitable for detecting labels of instances from both known and unknown classes. Particularly, we utilize a convolution neural network layer that aids in the learning of a latent feature space suitable for novel class detection. We empirically measure the performance of CSIM over multiple realworld image datasets and demonstrate its superiority by comparing its performance with existing semi-supervised methods.


Distribution Networks for Open Set Learning

In open set learning, a model must be able to generalize to novel classe...

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

Deep Neural Network (DNN) has been largely demonstrated to be effective ...

Calibrated Simplex Mapping Classification

We propose a novel supervised multi-class/single-label classifier that m...

A Segmentation-Oriented Inter-Class Transfer Method: Application to Retinal Vessel Segmentation

Retinal vessel segmentation, as a principal nonintrusive diagnose method...

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

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

Do Neural Network Weights account for Classes Centers?

The exploitation of Deep Neural Networks (DNNs) as descriptors in featur...