Saved in:
Bibliographic Details
Main Authors: Wang, Ye-Wen, Zong, Chen-Chen, Xie, Ming-Kun, Huang, Sheng-Jun
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.17607
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913519536963584
author Wang, Ye-Wen
Zong, Chen-Chen
Xie, Ming-Kun
Huang, Sheng-Jun
author_facet Wang, Ye-Wen
Zong, Chen-Chen
Xie, Ming-Kun
Huang, Sheng-Jun
contents Active learning (AL) has achieved great success by selecting the most valuable examples from unlabeled data. However, they usually deteriorate in real scenarios where open-set noise gets involved, which is studied as open-set annotation (OSA). In this paper, we owe the deterioration to the unreliable predictions arising from softmax-based translation invariance and propose a Dirichlet-based Coarse-to-Fine Example Selection (DCFS) strategy accordingly. Our method introduces simplex-based evidential deep learning (EDL) to break translation invariance and distinguish known and unknown classes by considering evidence-based data and distribution uncertainty simultaneously. Furthermore, hard known-class examples are identified by model discrepancy generated from two classifier heads, where we amplify and alleviate the model discrepancy respectively for unknown and known classes. Finally, we combine the discrepancy with uncertainties to form a two-stage strategy, selecting the most informative examples from known classes. Extensive experiments on various openness ratio datasets demonstrate that DCFS achieves state-of-art performance.
format Preprint
id arxiv_https___arxiv_org_abs_2409_17607
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Dirichlet-Based Coarse-to-Fine Example Selection For Open-Set Annotation
Wang, Ye-Wen
Zong, Chen-Chen
Xie, Ming-Kun
Huang, Sheng-Jun
Artificial Intelligence
Active learning (AL) has achieved great success by selecting the most valuable examples from unlabeled data. However, they usually deteriorate in real scenarios where open-set noise gets involved, which is studied as open-set annotation (OSA). In this paper, we owe the deterioration to the unreliable predictions arising from softmax-based translation invariance and propose a Dirichlet-based Coarse-to-Fine Example Selection (DCFS) strategy accordingly. Our method introduces simplex-based evidential deep learning (EDL) to break translation invariance and distinguish known and unknown classes by considering evidence-based data and distribution uncertainty simultaneously. Furthermore, hard known-class examples are identified by model discrepancy generated from two classifier heads, where we amplify and alleviate the model discrepancy respectively for unknown and known classes. Finally, we combine the discrepancy with uncertainties to form a two-stage strategy, selecting the most informative examples from known classes. Extensive experiments on various openness ratio datasets demonstrate that DCFS achieves state-of-art performance.
title Dirichlet-Based Coarse-to-Fine Example Selection For Open-Set Annotation
topic Artificial Intelligence
url https://arxiv.org/abs/2409.17607