Supervision : Hichem SAHBI

Co-supervision : STOIAN Andrei

Deep Active Learning for Visual Recognition with Few Examples

Automatic image analysis has improved the exploitation of image sensors, with data coming from different sensors such as phone cameras, surveillance cameras, satellite imagers or even drones. Deep learning achieves excellent results in image analysis applications where large amounts of annotated data are available, but learning a new image classifier from scratch is a difficult task. Most image classification methods are supervised, requiring annotations, which is a significant investment. Different frugal learning solutions (with few annotated examples) exist, including transfer learning, active learning, semi-supervised learning or meta-learning. The goal of this thesis is to study these frugal learning solutions for visual recognition tasks, namely image classification and change detection in satellite images. The classifier is trained iteratively by starting with only a few annotated samples, and asking the user to annotate as few data as possible to obtain satisfactory performance. Deep active learning was initially studied with other methods and suited our operational problem the most, so we chose this solution. In this thesis, we have developed an interactive approach, where we ask the most informative questions about the relevance of the data to an oracle (annotator). Based on its answers, a decision function is iteratively updated. We model the probability that the samples are relevant, by minimizing an objective function capturing the representativeness, diversity and ambiguity of the data. Data with high probability are then selected for annotation. We have improved this approach, using reinforcement learning to dynamically and accurately weight the importance of representativeness, diversity and ambiguity of the data in each active learning cycle. Finally, our last approach consists of a display model that selects the most representative and diverse virtual examples, which adversely challenge the learned model, in order to obtain a highly discriminative model in subsequent iterations of active learning. The good results obtained against the different baselines and the state of the art in the tasks of satellite image change detection and image classification have demonstrated the relevance of the proposed frugal learning models.

2021-2023 Publications

• 2023
  • S. Deschamps : “Apprentissage actif profond pour la reconnaissance visuelle à partir de peu d’exemples”, thesis, phd defence 06/15/2023, supervision Sahbi, Hichem, co-supervision : Stoian, Andrei (2023)
  • H. Sahbi, S. Deschamps : “ADVERSARIAL LABEL-EFFICIENT SATELLITE IMAGE CHANGE DETECTION”, IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Pasadena, United States, pp. 5794-5797, (IEEE) (2023)
  • H. Sahbi, S. Deschamps : “DEEP-NET INVERSION FOR FRUGAL SATELLITE IMAGE CHANGE DETECTION”, IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Pasadena, United States, pp. 6470-6473, (IEEE) (2023)
• 2022
  • S. Deschamps, H. Sahbi : “Reinforcement-based Display Selection for Frugal Learning”, International Conference on Pattern Recognition (ICPR), Montréal, Canada (2022)
  • H. Sahbi, S. Deschamps : “LEARNING VIRTUAL EXEMPLARS FOR LABEL-EFFICIENT SATELLITE IMAGE CHANGE DETECTION”, IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium, Kuala Lumpur, Malaysia, pp. 1197-1200, (IEEE) (2022)
  • S. Deschamps, H. Sahbi : “REINFORCEMENT-BASED FRUGAL LEARNING FOR INTERACTIVE SATELLITE IMAGE CHANGE DETECTION”, IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium, Kuala Lumpur, Malaysia, pp. 627-630, (IEEE) (2022)
• 2021
  • H. Sahbi, S. Deschamps, A. Stoian : “Frugal Learning for Interactive Satellite Image Change Detection”, 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, Brussels, Belgium, pp. 2811-2814 (2021)