Adaptive Image Stream Classification via Convolutional Neural Network with Intrinsic Similarity Metrics
This addresses the problem of open-world classification for image streams, which is incremental as it builds on existing semi-supervised methods.
The paper tackles the challenge of novel class detection in image streams by proposing CSIM, a semi-supervised multi-task learning framework that learns a latent feature space for detecting both known and unknown classes, demonstrating superiority over existing methods on real-world image datasets.
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.