5 papers
Self-supervised structured object representation learning
Oussama Hadjerci, Antoine Letienne, Mohamed Abbas Hedjazi +1
Self-supervised learning (SSL) has emerged as a powerful technique for learning visual representations. While recent SSL approaches achieve strong results in global image understan…
Enhancing knowledge retention for continual learning with domain-specific adapters and features gating
Mohamed Abbas Hedjazi, Oussama Hadjerci, Adel Hafiane
Continual learning empowers models to learn from a continuous stream of data while preserving previously acquired knowledge, effectively addressing the challenge of catastrophic fo…
Single image calibration using knowledge distillation approaches
Khadidja Ould Amer, Oussama Hadjerci, Mohamed Abbas Hedjazi +1
Although recent deep learning-based calibration methods can predict extrinsic and intrinsic camera parameters from a single image, their generalization remains limited by the numbe…
Efficient texture-aware multi-GAN for image inpainting
Mohamed Abbas Hedjazi, Yakup Genc
Recent GAN-based (Generative adversarial networks) inpainting methods show remarkable improvements and generate plausible images using multi-stage networks or Contextual Attention…
Learning to Inpaint by Progressively Growing the Mask Regions
Mohamed Abbas Hedjazi, Yakup Genc
Image inpainting is one of the most challenging tasks in computer vision. Recently, generative-based image inpainting methods have been shown to produce visually plausible images.…