OpenHAIV: A Framework Towards Practical Open-World Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915437824966656 |
|---|---|
| author | Xiang, Xiang Zhou, Qinhao Xu, Zhuo Ma, Jing Dai, Jiaxin Liang, Yifan Li, Hanlin |
| author_facet | Xiang, Xiang Zhou, Qinhao Xu, Zhuo Ma, Jing Dai, Jiaxin Liang, Yifan Li, Hanlin |
| contents | 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 . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_07270 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | OpenHAIV: A Framework Towards Practical Open-World Learning Xiang, Xiang Zhou, Qinhao Xu, Zhuo Ma, Jing Dai, Jiaxin Liang, Yifan Li, Hanlin Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Image and Video Processing 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 . |
| title | OpenHAIV: A Framework Towards Practical Open-World Learning |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Image and Video Processing |
| url | https://arxiv.org/abs/2508.07270 |