Skip to Main content Skip to Navigation

Continual learning for image classification

Abstract : This thesis deals with deep learning applied to image classification tasks. The primary motivation for the work is to make current deep learning techniques more efficient and to deal with changes in the data distribution. We work in the broad framework of continual learning, with the aim to have in the future machine learning models that can continuously improve.We first look at change in label space of a data set, with the data samples themselves remaining the same. We consider a semantic label hierarchy to which the labels belong. We investigate how we can utilise this hierarchy for obtaining improvements in models which were trained on different levels of this hierarchy.The second and third contribution involve continual learning using a generative model. We analyse the usability of samples from a generative model in the case of training good discriminative classifiers. We propose techniques to improve the selection and generation of samples from a generative model. Following this, we observe that continual learning algorithms do undergo some loss in performance when trained on several tasks sequentially. We analyse the training dynamics in this scenario and compare with training on several tasks simultaneously. We make observations that point to potential difficulties in the learning of models in a continual learning scenario.Finally, we propose a new design template for convolutional networks. This architecture leads to training of smaller models without compromising performance. In addition the design lends itself to easy parallelisation, leading to efficient distributed training.In conclusion, we look at two different types of continual learning scenarios. We propose methods that lead to improvements. Our analysis also points to greater issues, to over come which we might need changes in our current neural network training procedure.
Document type :
Complete list of metadatas

Cited literature [122 references]  Display  Hide  Download
Contributor : Abes Star :  Contact
Submitted on : Monday, July 27, 2020 - 2:38:12 PM
Last modification on : Tuesday, October 6, 2020 - 4:20:06 PM


Version validated by the jury (STAR)


  • HAL Id : tel-02907322, version 1




Anuvabh Dutt. Continual learning for image classification. Artificial Intelligence [cs.AI]. Université Grenoble Alpes, 2019. English. ⟨NNT : 2019GREAM063⟩. ⟨tel-02907322⟩



Record views


Files downloads