Category: WACV

  • Plasticity-Optimized Complementary Networks for Unsupervised Continual Learning

    Alex Gomez-Villa, Bartlomiej Twardowski, Kai Wang, Joost van de Weijer Read Full Paper → Continuous unsupervised representation learning (CURL) research has greatly benefited from improvements in self-supervised learning (SSL) techniques. As a result, existing CURL methods using SSL can learn high-quality representations without any labels, but with a notable performance drop when learning on a […]

  • Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-Free Continual Learning

    Filip Szatkowski, Mateusz Pyla, Marcin Przewięźlikowski, Sebastian Cygert, Bartłomiej Twardowski, Tomasz Trzciński Read Full Paper → In this work, we investigate exemplar-free class incremental learning (CIL) with knowledge distillation (KD) as a regularization strategy, aiming to prevent forgetting. KD-based methods are successfully used in CIL, but they often struggle to regularize the model without access […]

  • Attribution-aware Weight Transfer: A Warm-Start Initialization for Class-Incremental Semantic Segmentation

    Dipam Goswami, René Schuster, Joost van de Weijer, Didier Stricker Read Full Paper → In class-incremental semantic segmentation (CISS), deep learning architectures suffer from the critical problems of catastrophic forgetting and semantic background shift. Although recent works focused on these issues, existing classifier initialization methods do not address the background shift problem and assign the same initialization weights […]

  • Class-Balanced Active Learning for Image Classification

    Javad Zolfaghari Bengar, Joost van de Weijer, Laura Lopez Fuentes, Bogdan Raducanu Read Full Paper → Active learning aims to reduce the labeling effort that is required to train algorithms by learning an acquisition function selecting the most relevant data for which a label should be requested from a large unlabeled data pool. Active learning is generally studied […]

  • Bandwidth Limited Object Recognition in High Resolution Imagery

    Laura Lopez-Fuentes; Andrew D. Bagdanov; Joost Van De Weijer; Harald Skinnemoen Read Full Paper → This paper proposes a novel method to optimize bandwidth usage for object detection in critical communication scenarios. We develop two operating models of active information seeking. The first model identifies promising regions in low resolution imagery and progressively requests higher resolution regions on […]