A Review of Open-World Learning and Steps Toward Open-World Learning Without Labels

• URL: http://arxiv.org/abs/2011.12906v3
• Date: Mon, 3 Jan 2022 14:34:53 GMT
• Title: A Review of Open-World Learning and Steps Toward Open-World Learning Without Labels
• Authors: Mohsen Jafarzadeh, Akshay Raj Dhamija, Steve Cruz, Chunchun Li, Touqeer Ahmad, Terrance E. Boult
• Abstract summary: In open-world learning, an agent starts with a set of known classes, detects, and manages things that it does not know, and learns them over time from a non-stationary stream of data. This paper formalizes various open-world learning problems including open-world learning without labels.
• Score: 11.380522815465984
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In open-world learning, an agent starts with a set of known classes, detects, and manages things that it does not know, and learns them over time from a non-stationary stream of data. Open-world learning is related to but also distinct from a multitude of other learning problems and this paper briefly analyzes the key differences between a wide range of problems including incremental learning, generalized novelty discovery, and generalized zero-shot learning. This paper formalizes various open-world learning problems including open-world learning without labels. These open-world problems can be addressed with modifications to known elements, we present a new framework that enables agents to combine various modules for novelty-detection, novelty-characterization, incremental learning, and instance management to learn new classes from a stream of unlabeled data in an unsupervised manner, survey how to adapt a few state-of-the-art techniques to fit the framework and use them to define seven baselines for performance on the open-world learning without labels problem. We then discuss open-world learning quality and analyze how that can improve instance management. We also discuss some of the general ambiguity issues that occur in open-world learning without labels.

Related papers

• Towards Few-Shot Learning in the Open World: A Review and Beyond [52.41344813375177]
  Few-shot learning aims to mimic human intelligence by enabling significant generalizations and transferability. This paper presents a review of recent advancements designed to adapt FSL for use in open-world settings. We categorize existing methods into three distinct types of open-world few-shot learning: those involving varying instances, varying classes, and varying distributions.
  arXiv  Detail & Related papers  (2024-08-19T06:23:21Z)
• Open-world Machine Learning: A Review and New Outlooks [83.6401132743407]
  This paper aims to provide a comprehensive introduction to the emerging open-world machine learning paradigm. It aims to help researchers build more powerful AI systems in their respective fields, and to promote the development of artificial general intelligence.
  arXiv  Detail & Related papers  (2024-03-04T06:25:26Z)
• Open Long-Tailed Recognition in a Dynamic World [82.91025831618545]
  Real world data often exhibits a long-tailed and open-ended (with unseen classes) distribution. A practical recognition system must balance between majority (head) and minority (tail) classes, generalize across the distribution, and acknowledge novelty upon the instances of unseen classes (open classes) We define Open Long-Tailed Recognition++ as learning from such naturally distributed data and optimizing for the classification accuracy over a balanced test set.
  arXiv  Detail & Related papers  (2022-08-17T15:22:20Z)
• Open Environment Machine Learning [84.90891046882213]
  Conventional machine learning studies assume close world scenarios where important factors of the learning process hold invariant. This article briefly introduces some advances in this line of research, focusing on techniques concerning emerging new classes, decremental/incremental features, changing data distributions, varied learning objectives, and discusses some theoretical issues.
  arXiv  Detail & Related papers  (2022-06-01T11:57:56Z)
• 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)
• Open-world Machine Learning: Applications, Challenges, and Opportunities [0.7734726150561086]
  Open-world machine learning deals with arbitrary inputs (data with unseen classes) to machine learning systems. Traditional machine learning is static learning which is not appropriate for an active environment. This paper presents a systematic review of various techniques for open-world machine learning.
  arXiv  Detail & Related papers  (2021-05-27T21:05:10Z)
• Task-Adaptive Negative Class Envision for Few-Shot Open-Set Recognition [36.53830822788852]
  We study the problem of few-shot open-set recognition (FSOR), which learns a recognition system robust to queries from new sources. We propose a novel task-adaptive negative class envision method (TANE) to model the open world. Our approach significantly improves the state-of-the-art performance on few-shot open-set recognition.
  arXiv  Detail & Related papers  (2020-12-24T02:30:18Z)
• Learnability with Indirect Supervision Signals [74.39088325025378]
  Learning from indirect supervision signals is important in real-world AI applications when, often, gold labels are missing or too costly. We develop a unified theoretical framework for multi-class classification when the supervision is provided by a variable that contains nonzero mutual information with the gold label. Our framework relaxes assumptions made in the literature, and supports learning with unknown, non-invertible and instance-dependent transitions.
  arXiv  Detail & Related papers  (2020-06-15T21:57:11Z)

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.