Reinforcement-based Display Selection for Frugal Learning - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Reinforcement-based Display Selection for Frugal Learning

Hichem Sahbi

Résumé

Most of the existing learning models, particularly deep neural networks, are reliant on large datasets whose handlabeling is expensive and time demanding. A current trend is to make the learning of these models frugal and less dependent on large collections of labeled data. Among the existing solutions, deep active learning is currently witnessing a major interest and its purpose is to train deep networks using as few labeled samples as possible. However, the success of active learning is highly dependent on how critical are these samples when training models. In this paper, we devise a novel active learning approach for label-efficient training. The proposed method is iterative and aims at minimizing a constrained objective function that mixes diversity, representativity and uncertainty criteria. The proposed approach is probabilistic and unifies all these criteria in a single objective function whose solution models the probability of relevance of samples (i.e., how critical) when learning a decision function. We also introduce a novel weighting mechanism based on reinforcement learning, which adaptively balances these criteria at each training iteration, using a particular stateless Q-learning model. Extensive experiments conducted on staple image classification data, including Object-DOTA, show the effectiveness of our proposed model w.r.t. several baselines including random, uncertainty and flat as well as other work.
Fichier principal
Vignette du fichier
paper.pdf (557.04 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03848481 , version 1 (10-11-2022)

Identifiants

  • HAL Id : hal-03848481 , version 1

Citer

Sébastien Deschamps, Hichem Sahbi. Reinforcement-based Display Selection for Frugal Learning. International Conference on Pattern Recognition (ICPR), Aug 2022, Montréal, Canada. ⟨hal-03848481⟩
43 Consultations
52 Téléchargements

Partager

Gmail Facebook X LinkedIn More