Rethinking Epistemic and Aleatoric Uncertainty for Active Open-Set Annotation: An Energy-Based Approach

• URL: http://arxiv.org/abs/2502.19691v2
• Date: Fri, 14 Mar 2025 11:32:24 GMT
• Title: Rethinking Epistemic and Aleatoric Uncertainty for Active Open-Set Annotation: An Energy-Based Approach
• Authors: Chen-Chen Zong, Sheng-Jun Huang,
• Abstract summary: Active learning faces significant challenges in the presence of open-set classes.<n>Existing methods either prioritize query examples likely to belong to known classes, or focus on querying those with highly uncertain predictions.<n>We propose an Energy-based Active Open-set framework, which effectively integrates EU and AU to achieve superior performance.
• Score: 32.80889742257346
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Active learning (AL), which iteratively queries the most informative examples from a large pool of unlabeled candidates for model training, faces significant challenges in the presence of open-set classes. Existing methods either prioritize query examples likely to belong to known classes, indicating low epistemic uncertainty (EU), or focus on querying those with highly uncertain predictions, reflecting high aleatoric uncertainty (AU). However, they both yield suboptimal performance, as low EU corresponds to limited useful information, and closed-set AU metrics for unknown class examples are less meaningful. In this paper, we propose an Energy-based Active Open-set Annotation (EAOA) framework, which effectively integrates EU and AU to achieve superior performance. EAOA features a $(C+1)$-class detector and a target classifier, incorporating an energy-based EU measure and a margin-based energy loss designed for the detector, alongside an energy-based AU measure for the target classifier. Another crucial component is the target-driven adaptive sampling strategy. It first forms a smaller candidate set with low EU scores to ensure closed-set properties, making AU metrics meaningful. Subsequently, examples with high AU scores are queried to form the final query set, with the candidate set size adjusted adaptively. Extensive experiments show that EAOA achieves state-of-the-art performance while maintaining high query precision and low training overhead. The code is available at https://github.com/chenchenzong/EAOA.

Related papers

• Beyond Exact Match: Semantically Reassessing Event Extraction by Large Language Models [69.38024658668887]
  Current evaluation method for event extraction relies on token-level exact match. We propose RAEE, an automatic evaluation framework that accurately assesses event extraction results at semantic-level instead of token-level.
  arXiv  Detail & Related papers  (2024-10-12T07:54:01Z)
• Prompt Optimization with EASE? Efficient Ordering-aware Automated Selection of Exemplars [66.823588073584]
  Large language models (LLMs) have shown impressive capabilities in real-world applications. The quality of these exemplars in the prompt greatly impacts performance. Existing methods fail to adequately account for the impact of exemplar ordering on the performance.
  arXiv  Detail & Related papers  (2024-05-25T08:23:05Z)
• Open-Set Recognition in the Age of Vision-Language Models [9.306738687897889]
  We investigate whether vision-language models (VLMs) for open-vocabulary perception inherently open-set models because they are trained on internet-scale datasets. We find they introduce closed-set assumptions via their finite query set, making them vulnerable to open-set conditions. We show that naively increasing the size of the query set to contain more and more classes does not mitigate this problem, but instead causes diminishing task performance and open-set performance.
  arXiv  Detail & Related papers  (2024-03-25T08:14:22Z)
• How to Evaluate the Generalization of Detection? A Benchmark for Comprehensive Open-Vocabulary Detection [25.506346503624894]
  We propose a new benchmark named OVDEval, which includes 9 sub-tasks and introduces evaluations on commonsense knowledge. The dataset is meticulously created to provide hard negatives that challenge models' true understanding of visual and linguistic input.
  arXiv  Detail & Related papers  (2023-08-25T04:54:32Z)
• Glocal Energy-based Learning for Few-Shot Open-Set Recognition [57.84234213466372]
  Few-shot open-set recognition (FSOR) is a challenging task of great practical value. We propose a novel energy-based hybrid model for FSOR. Experiments on three standard FSOR datasets show the superior performance of our model.
  arXiv  Detail & Related papers  (2023-04-24T07:06:50Z)
• OpenAUC: Towards AUC-Oriented Open-Set Recognition [151.5072746015253]
  Traditional machine learning follows a close-set assumption that the training and test set share the same label space. Open-Set Recognition (OSR) aims to make correct predictions on both close-set samples and open-set samples. To fix these issues, we propose a novel metric named OpenAUC.
  arXiv  Detail & Related papers  (2022-10-22T08:54:15Z)
• Active Pointly-Supervised Instance Segmentation [106.38955769817747]
  We present an economic active learning setting, named active pointly-supervised instance segmentation (APIS) APIS starts with box-level annotations and iteratively samples a point within the box and asks if it falls on the object. The model developed with these strategies yields consistent performance gain on the challenging MS-COCO dataset.
  arXiv  Detail & Related papers  (2022-07-23T11:25:24Z)
• Active Learning for Open-set Annotation [38.739845944840454]
  We propose a new active learning framework called LfOSA, which boosts the classification performance with an effective sampling strategy to precisely detect examples from known classes for annotation. The experimental results show that the proposed method can significantly improve the selection quality of known classes, and achieve higher classification accuracy with lower annotation cost than state-of-the-art active learning methods.
  arXiv  Detail & Related papers  (2022-01-18T06:11:51Z)
• Prior Guided Feature Enrichment Network for Few-Shot Segmentation [64.91560451900125]
  State-of-the-art semantic segmentation methods require sufficient labeled data to achieve good results. Few-shot segmentation is proposed to tackle this problem by learning a model that quickly adapts to new classes with a few labeled support samples. Theses frameworks still face the challenge of generalization ability reduction on unseen classes due to inappropriate use of high-level semantic information.
  arXiv  Detail & Related papers  (2020-08-04T10:41:32Z)

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.