Difficulty-Aware Simulator for Open Set Recognition

TL;DR

This paper introduces DIAS, a difficulty-aware simulator that generates diverse fake samples to improve open set recognition by better modeling unknowns with varying difficulty levels.

Contribution

The paper proposes a novel framework, DIAS, which creates difficulty-aware fake samples using GANs and Copycat to enhance open set recognition performance.

Findings

DIAS outperforms state-of-the-art methods on AUROC and F-score metrics.

Generated samples with varying difficulty levels improve model robustness.

The approach effectively simulates real-world open set scenarios.

Abstract

Open set recognition (OSR) assumes unknown instances appear out of the blue at the inference time. The main challenge of OSR is that the response of models for unknowns is totally unpredictable. Furthermore, the diversity of open set makes it harder since instances have different difficulty levels. Therefore, we present a novel framework, DIfficulty-Aware Simulator (DIAS), that generates fakes with diverse difficulty levels to simulate the real world. We first investigate fakes from generative adversarial network (GAN) in the classifier's viewpoint and observe that these are not severely challenging. This leads us to define the criteria for difficulty by regarding samples generated with GANs having moderate-difficulty. To produce hard-difficulty examples, we introduce Copycat, imitating the behavior of the classifier. Furthermore, moderate- and easy-difficulty samples are also yielded by our modified GAN and Copycat, respectively. As a result, DIAS outperforms state-of-the-art methods with both metrics of AUROC and F-score. Our code is available at https://github.com/wjun0830/Difficulty-Aware-Simulator.