Deep Compact Polyhedral Conic Classifier for Open and Closed Set Recognition
This work addresses visual classification challenges, including anomaly detection, with a novel approach that improves recognition in open set scenarios, representing a strong specific gain rather than a foundational advancement.
The paper tackles the problem of open and closed set recognition by proposing a deep neural network classifier that maximizes inter-class separation and minimizes intra-class variation using a polyhedral conic function, achieving state-of-the-art performance, particularly in open set recognition tasks.
In this paper, we propose a new deep neural network classifier that simultaneously maximizes the inter-class separation and minimizes the intra-class variation by using the polyhedral conic classification function. The proposed method has one loss term that allows the margin maximization to maximize the inter-class separation and another loss term that controls the compactness of the class acceptance regions. Our proposed method has a nice geometric interpretation using polyhedral conic function geometry. We tested the proposed method on various visual classification problems including closed/open set recognition and anomaly detection. The experimental results show that the proposed method typically outperforms other state-of-the art methods, and becomes a better choice compared to other tested methods especially for open set recognition type problems.