Recognition Awareness: An Application of Latent Cognizance to Open-Set Recognition

TL;DR

This paper introduces Latent Cognizance, a novel approach for open-set recognition that reinterprets softmax outputs using Bayesian principles to better identify foreign objects in diverse recognition scenarios.

Contribution

It proposes a new probabilistic interpretation of softmax for open-set recognition, enabling more accurate detection of unknown objects compared to traditional methods.

Findings

LC outperforms existing OSR methods on Imagenet 2012.

Effective in identifying foreign objects in diverse scenarios.

Supports the hypothesis that Bayesian reinterpretation improves OSR.

Abstract

This study investigates an application of a new probabilistic interpretation of a softmax output to Open-Set Recognition (OSR). Softmax is a mechanism wildly used in classification and object recognition. However, a softmax mechanism forces a model to operate under a closed-set paradigm, i.e., to predict an object class out of a set of pre-defined labels. This characteristic contributes to efficacy in classification, but poses a risk of non-sense prediction in object recognition. Object recognition is often operated under a dynamic and diverse condition. A foreign object -- an object of any unprepared class -- can be encountered at any time. OSR is intended to address an issue of identifying a foreign object in object recognition. Based on Bayes theorem and the emphasis of conditioning on the context, softmax inference has been re-interpreted. This re-interpretation has led to a new approach to OSR, called Latent Cognizance (LC). Our investigation employs various scenarios, using Imagenet 2012 dataset as well as fooling and open-set images. The findings support LC hypothesis and show its effectiveness on OSR.