Skip to Main content Skip to Navigation

Weakly supervised learning for image classification and potentially moving obstacles analysis

Abstract : In the context of autonomous vehicle perception, the interest of the research community for deep learning approaches has continuously grown since the last decade. This can be explained by the fact that deep learning techniques provide nowadays state-of-the-art prediction performances for several computer vision challenges. More specifically, deep learning techniques can provide rich semantic information concerning the complex visual patterns encountered in autonomous driving scenarios. However, such approaches require, as their name implies, to learn on data. In particular, state-of-the-art prediction performances on discriminative tasks often demand hand labeled data of the target application domain. Hand labeling has a significant cost, while, conversely, unlabeled data can be easily obtained in the autonomous driving context. It turns out that a category of learning strategies, referred to as weakly supervised learning, enables to exploit partially labeled data. Therefore, we aim in this thesis at reducing as much as possible the hand labeling requirement by proposing weakly supervised learning techniques.We start by presenting a type of learning methods which are self-supervised. They consist of substituting hand-labels by upstream techniques able to automatically generate exploitable training labels. Self-supervised learning (SSL) techniques have proven their usefulness in the past for offroad obstacles avoidance and path planning through changing environments. However, SSL techniques still leave the door open for detection, segmentation, and classification of static potentially moving obstacles.Consequently, we propose in this thesis three novel weakly supervised learning methods with the final goal to deal with such road users through an SSL framework. The first two proposed contributions of this work aim at dealing with partially labeled image classification datasets, such that the labeling effort can be only focused on our class of interest, the positive class. Then, we propose an approach which deals with training data containing a high fraction of wrong labels, referred to as noisy labels. Next, we demonstrate the potential of such weakly supervised strategies for detection and segmentation of potentially moving obstacles.
Complete list of metadatas

Cited literature [200 references]  Display  Hide  Download
Contributor : Abes Star :  Contact
Submitted on : Friday, June 26, 2020 - 10:23:12 AM
Last modification on : Tuesday, October 20, 2020 - 11:33:37 AM


Version validated by the jury (STAR)


  • HAL Id : tel-02881904, version 1


Florent Chiaroni. Weakly supervised learning for image classification and potentially moving obstacles analysis. Signal and Image processing. Université Paris-Saclay, 2020. English. ⟨NNT : 2020UPASC006⟩. ⟨tel-02881904⟩



Record views


Files downloads