OpenHAIV: A Framework Towards Practical Open-World Learning

TL;DR

OpenHAIV is a comprehensive framework that combines out-of-distribution detection, new class discovery, and incremental fine-tuning to enable models to autonomously learn and adapt in open-world environments.

Contribution

It introduces a unified pipeline integrating OOD detection, class discovery, and continual learning, addressing limitations of existing methods in open-world scenarios.

Findings

Effective in identifying unknown classes

Enables autonomous knowledge updates

Outperforms existing open-world learning methods

Abstract

Substantial progress has been made in various techniques for open-world recognition. Out-of-distribution (OOD) detection methods can effectively distinguish between known and unknown classes in the data, while incremental learning enables continuous model knowledge updates. However, in open-world scenarios, these approaches still face limitations. Relying solely on OOD detection does not facilitate knowledge updates in the model, and incremental fine-tuning typically requires supervised conditions, which significantly deviate from open-world settings. To address these challenges, this paper proposes OpenHAIV, a novel framework that integrates OOD detection, new class discovery, and incremental continual fine-tuning into a unified pipeline. This framework allows models to autonomously acquire and update knowledge in open-world environments. The proposed framework is available at https://haiv-lab.github.io/openhaiv .