Minority class oriented active learning for imbalanced datasets - CEA - Commissariat à l’énergie atomique et aux énergies alternatives Accéder directement au contenu
Poster De Conférence Année : 2021

Minority class oriented active learning for imbalanced datasets

Résumé

Active learning aims to optimize the dataset annotation process when resources are constrained. Most existing methods are designed for balanced datasets. Their practical applicability is limited by the fact that a majority of real-life datasets are actually imbalanced. Here, we introduce a new active learning method which is designed for imbalanced datasets. It favors samples likely to be in minority classes so as to reduce the imbalance of the labeled subset and create a better representation for these classes. We also compare two training schemes for active learning: (1) the one commonly deployed in deep active learning using model fine tuning for each iteration and (2) a scheme which is inspired by transfer learning and exploits generic pre-trained models and train shallow classifiers for each iteration. Evaluation is run with three imbalanced image datasets. Results show that the proposed active learning method outperforms competitive baselines. Equally interesting, they also indicate that the transfer learning training scheme outperforms model fine tuning if features are transferable from the generic dataset to the unlabeled one. This last result is surprising and should encourage the community to explore the design of deep active learning methods.
Fichier principal
Vignette du fichier
Iterative_al__icpr_NoteIEEECS.pdf (940.23 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

cea-04533119 , version 1 (04-04-2024)

Identifiants

Citer

Umang Aggarwal, Adrian Popescu, Céline Hudelot. Minority class oriented active learning for imbalanced datasets. ICPR 2020 - 25th International Conference on Pattern Recognition, Jan 2021, Virtual, Italy. , 2020 25th International Conference on Pattern Recognition (ICPR), Milan, Italy, 2021, pp.9920-9927, 2021, ⟨10.1109/ICPR48806.2021.9412182⟩. ⟨cea-04533119⟩
7 Consultations
4 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More