Filip Szatkowski

Publication Activity (10 Years)

Years Active: 2022-2024
Publications (10 Years): 12

Top Topics

Knowledge Acquired

Learner Centred

Distributed Representations

Top Venues

ICCV (Workshops)

Publications

Filip Szatkowski, Mateusz Pyla, Marcin Przewiezlikowski, Sebastian Cygert, Bartlomiej Twardowski, Tomasz Trzcinski
Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-free Continual Learning. WACV (2024)
Aleksandra Irena Nowak, Lukasz Gniecki, Filip Szatkowski, Jacek Tabor
Sparser, Better, Deeper, Stronger: Improving Sparse Training with Exact Orthogonal Initialization. CoRR (2024)
Filip Szatkowski, Fei Yang, Bartlomiej Twardowski, Tomasz Trzcinski, Joost van de Weijer
Accelerated Inference and Reduced Forgetting: The Dual Benefits of Early-Exit Networks in Continual Learning. CoRR (2024)
Filip Szatkowski, Mateusz Pyla, Marcin Przewiezlikowski, Sebastian Cygert, Bartlomiej Twardowski, Tomasz Trzcinski
Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-free Continual Learning. ICCV (Workshops) (2023)
Mikolaj Piórczynski, Filip Szatkowski, Klaudia Balazy, Bartosz Wójcik
Exploiting Transformer Activation Sparsity with Dynamic Inference. CoRR (2023)
Bartosz Wójcik, Marcin Przewiezlikowski, Filip Szatkowski, Maciej Wolczyk, Klaudia Balazy, Bartlomiej Krzepkowski, Igor T. Podolak, Jacek Tabor, Marek Smieja, Tomasz Trzcinski
Zero time waste in pre-trained early exit neural networks. Neural Networks 168 (2023)
Filip Szatkowski, Mateusz Pyla, Marcin Przewiezlikowski, Sebastian Cygert, Bartlomiej Twardowski, Tomasz Trzcinski
Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-free Continual Learning. CoRR (2023)
Filip Szatkowski, Karol J. Piczak, Przemyslaw Spurek, Jacek Tabor, Tomasz Trzcinski
Hypernetworks Build Implicit Neural Representations of Sounds. ECML/PKDD (4) (2023)
Filip Szatkowski, Karol J. Piczak, Przemyslaw Spurek, Jacek Tabor, Tomasz Trzcinski
Hypernetworks build Implicit Neural Representations of Sounds. CoRR (2023)
Stanislaw Pawlak, Filip Szatkowski, Michal Bortkiewicz, Jan Dubinski, Tomasz Trzcinski
Progressive Latent Replay for efficient Generative Rehearsal. CoRR (2022)
Stanislaw Pawlak, Filip Szatkowski, Michal Bortkiewicz, Jan Dubinski, Tomasz Trzcinski
Progressive Latent Replay for Efficient Generative Rehearsal. ICONIP (4) (2022)
Filip Szatkowski, Karol J. Piczak, Przemyslaw Spurek, Jacek Tabor, Tomasz Trzcinski
HyperSound: Generating Implicit Neural Representations of Audio Signals with Hypernetworks. CoRR (2022)