Thesis : Frugal Learning with Deep Generative Networks for Visual Scene Recognition
PhD school thesis
The goal of this thesis subject is to design novel deep continual learning models for visual recognition [13]. One of the main challenges is to design discriminative as well as generative networks that learn visual categories effectively while also attenuating catastrophic forgetting. The proposed solutions will be built upon deep variational auto-encoders (VAE) and generative adversarial networks (GANs) that allow mitigating CF with a reasonable growth in the number of training parameters, and memory footprint. The objectives also include (but not limited to)
- The design of new GANs/VAEs for image generation, augmentation and replay.
- The disentanglement and interpretation of different factors in these generative models including semantics, appearances and dynamics of the visual contents.
- The inclusion of these generative models in a whole framework that achieves continual learning while also handling the challenging issue of catastrophic forgetting.
- These networks should be designed in order to run, not only on standard GPUs, but also on edge devices including mobile phones and connected objects endowed with low computational and energy resources.
- Applications include continual object detection, image classification and segmentation in still and video sequences.
This PhD research project has been submitted for a funding request to “Ecole Doctorale d‘Informatique, Télécommunication et d‘Electronique (EDITE)”. The PhD candidate selected by the project leader will therefore participate in the project selection process (including a file and an interview) to obtain funding.
Contact :Hichem Sahbi