Learning Open Set Network with Discriminative Reciprocal Points

TL;DR

This paper introduces Reciprocal Point Learning (RPL), a novel framework for open set recognition that improves the classification of known and unknown samples by modeling extra-class space and reducing open space risk.

Contribution

It proposes the concept of reciprocal points and a new regularization method, enhancing open set recognition by learning more discriminative representations with only known class data.

Findings

Achieves state-of-the-art performance on open set benchmarks.

Introduces a new large-scale aircraft dataset for open set recognition.

Demonstrates the effectiveness of reciprocal points in reducing open space risk.

Abstract

Open set recognition is an emerging research area that aims to simultaneously classify samples from predefined classes and identify the rest as 'unknown'. In this process, one of the key challenges is to reduce the risk of generalizing the inherent characteristics of numerous unknown samples learned from a small amount of known data. In this paper, we propose a new concept, Reciprocal Point, which is the potential representation of the extra-class space corresponding to each known category. The sample can be classified to known or unknown by the otherness with reciprocal points. To tackle the open set problem, we offer a novel open space risk regularization term. Based on the bounded space constructed by reciprocal points, the risk of unknown is reduced through multi-category interaction. The novel learning framework called Reciprocal Point Learning (RPL), which can indirectly introduce the unknown information into the learner with only known classes, so as to learn more compact and discriminative representations. Moreover, we further construct a new large-scale challenging aircraft dataset for open set recognition: Aircraft 300 (Air-300). Extensive experiments on multiple benchmark datasets indicate that our framework is significantly superior to other existing approaches and achieves state-of-the-art performance on standard open set benchmarks.