Open-Set Recognition with Gradient-Based Representations

TL;DR

This paper introduces a gradient-based method for open-set recognition that effectively detects unknown classes without modeling their distribution, outperforming existing methods by up to 11.6%.

Contribution

It proposes using gradient representations from a known classifier to identify unknown inputs, eliminating the need for explicit unknown class modeling.

Findings

Outperforms state-of-the-art open-set recognition methods by up to 11.6%.

Utilizes gradient-based features to detect unknown classes effectively.

Compatible with any supervised classifier without additional unknown class data.

Abstract

Neural networks for image classification tasks assume that any given image during inference belongs to one of the training classes. This closed-set assumption is challenged in real-world applications where models may encounter inputs of unknown classes. Open-set recognition aims to solve this problem by rejecting unknown classes while classifying known classes correctly. In this paper, we propose to utilize gradient-based representations obtained from a known classifier to train an unknown detector with instances of known classes only. Gradients correspond to the amount of model updates required to properly represent a given sample, which we exploit to understand the model's capability to characterize inputs with its learned features. Our approach can be utilized with any classifier trained in a supervised manner on known classes without the need to model the distribution of unknown samples explicitly. We show that our gradient-based approach outperforms state-of-the-art methods by up to 11.6% in open-set classification.