OpenHAIV: A Framework Towards Practical Open-World Learning

• URL: http://arxiv.org/abs/2508.07270v1
• Date: Sun, 10 Aug 2025 09:55:19 GMT
• Title: OpenHAIV: A Framework Towards Practical Open-World Learning
• Authors: Xiang Xiang, Qinhao Zhou, Zhuo Xu, Jing Ma, Jiaxin Dai, Yifan Liang, Hanlin Li,
• Abstract summary: This paper proposes OpenHAIV, a novel framework for open-world recognition.<n>It integrates OOD detection, new class discovery, and incremental continual fine-tuning into a unified pipeline.<n>This framework allows models to autonomously acquire and update knowledge in open-world environments.
• Score: 15.287155720966998
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 .

Related papers

• Integration of Old and New Knowledge for Generalized Intent Discovery: A Consistency-driven Prototype-Prompting Framework [49.60947755616314]
  Generalized Intent Discovery (GID) addresses this by leveraging unlabeled OOD data to discover new intents without additional annotation.<n>We propose a consistency-driven prototype-prompting framework for GID from the perspective of integrating old and new knowledge.<n>Our method significantly outperforms all baseline methods, achieving state-of-the-art results.
  arXiv  Detail & Related papers  (2025-06-10T06:30:17Z)
• Improving Open-world Continual Learning under the Constraints of Scarce Labeled Data [19.168022702075774]
  Openworld continual learning (OWCL) adapts to sequential tasks with open samples, learning knowledge incrementally while preventing forgetting.<n>We propose a novel OFCL framework that integrates three key components: (1) an instance-wise token augmentation (ITA) that represents and enriches sample representations with additional knowledge, (2) a margin-based open boundary (MOB) that supports open detection with new tasks, and (3) an adaptive knowledge space (AKS) that endows unknowns with knowledge for the updating from unknowns to knowns.
  arXiv  Detail & Related papers  (2025-02-28T11:39:18Z)
• Exploring Open-world Continual Learning with Knowns-Unknowns Knowledge Transfer [10.426450189369266]
  Open-World Continual Learning (OWCL) is a challenging paradigm where models must incrementally learn new knowledge without forgetting while operating under an open-world assumption.<n>We propose textbfHoliTrans (Holistic Knowns-Unknowns Knowledge Transfer), a novel OWCL framework that integrates nonlinear random projection (NRP) to create an adaptive knowledge space.
  arXiv  Detail & Related papers  (2025-02-27T14:16:01Z)
• Deep Active Learning in the Open World [13.2318584850986]
  Machine learning models deployed in open-world scenarios often encounter unfamiliar conditions and perform poorly in unanticipated situations.<n>We introduce ALOE, a novel active learning algorithm for open-world environments designed to enhance model adaptation by incorporating new OOD classes.<n>Our findings reveal a crucial tradeoff between enhancing known-class performance and discovering new classes, setting the stage for future advancements in open-world machine learning.
  arXiv  Detail & Related papers  (2024-11-10T04:04:20Z)
• A Unified and General Framework for Continual Learning [58.72671755989431]
  Continual Learning (CL) focuses on learning from dynamic and changing data distributions while retaining previously acquired knowledge. Various methods have been developed to address the challenge of catastrophic forgetting, including regularization-based, Bayesian-based, and memory-replay-based techniques. This research aims to bridge this gap by introducing a comprehensive and overarching framework that encompasses and reconciles these existing methodologies.
  arXiv  Detail & Related papers  (2024-03-20T02:21:44Z)
• Open-world machine learning: A review and new outlooks [117.33922838201993]
  Article presents a holistic view of open-world machine learning.<n>It investigates unknown rejection, novelty discovery, and continual learning.<n>It aims to help researchers build more powerful AI systems in their respective fields.
  arXiv  Detail & Related papers  (2024-03-04T06:25:26Z)
• NovaCOMET: Open Commonsense Foundation Models with Symbolic Knowledge Distillation [82.85412355714898]
  We present NovaCOMET, an open commonsense knowledge model, that combines the best aspects of knowledge and general task models. Compared to previous knowledge models, NovaCOMET allows open-format relations enabling direct application to reasoning tasks. It explicitly centers knowledge, enabling superior performance for commonsense reasoning.
  arXiv  Detail & Related papers  (2023-12-10T19:45:24Z)
• Detecting and Learning Out-of-Distribution Data in the Open world: Algorithm and Theory [15.875140867859209]
  This thesis makes contributions to the realm of machine learning, specifically in the context of open-world scenarios. Research investigates two intertwined steps essential for open-world machine learning: Out-of-distribution (OOD) Detection and Open-world Representation Learning (ORL)
  arXiv  Detail & Related papers  (2023-10-10T00:25:21Z)
• Prompt-driven efficient Open-set Semi-supervised Learning [52.30303262499391]
  Open-set semi-supervised learning (OSSL) has attracted growing interest, which investigates a more practical scenario where out-of-distribution (OOD) samples are only contained in unlabeled data. We propose a prompt-driven efficient OSSL framework, called OpenPrompt, which can propagate class information from labeled to unlabeled data with only a small number of trainable parameters.
  arXiv  Detail & Related papers  (2022-09-28T16:25:08Z)
• Bayesian Embeddings for Few-Shot Open World Recognition [60.39866770427436]
  We extend embedding-based few-shot learning algorithms to the open-world recognition setting. We benchmark our framework on open-world extensions of the common MiniImageNet and TieredImageNet few-shot learning datasets.
  arXiv  Detail & Related papers  (2021-07-29T00:38:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.