19 citations · 29 across the 6 of their papers we have counts for
6 papers
Adaptive Computation Modules: Granular Conditional Computation For Efficient Inference
Bartosz Wójcik, Alessio Devoto, Karol Pustelnik +2
While transformer models have been highly successful, they are computationally inefficient. We observe that for each layer, the full width of the layer may be needed only for a sma…
Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion
Filip Szatkowski, Bartosz Wójcik, Mikołaj Piórczyński +1
Transformer models can face practical limitations due to their high computational requirements. At the same time, such models exhibit significant activation sparsity, which can be…
Face Identity-Aware Disentanglement in StyleGAN
Adrian Suwała, Bartosz Wójcik, Magdalena Proszewska +3
Conditional GANs are frequently used for manipulating the attributes of face images, such as expression, hairstyle, pose, or age. Even though the state-of-the-art models successful…
Computer Vision based inspection on post-earthquake with UAV synthetic dataset
Mateusz Żarski, Bartosz Wójcik, Jarosław A. Miszczak +2
The area affected by the earthquake is vast and often difficult to entirely cover, and the earthquake itself is a sudden event that causes multiple defects simultaneously, that can…
SLOVA: Uncertainty Estimation Using Single Label One-Vs-All Classifier
Bartosz Wójcik, Jacek Grela, Marek Śmieja +2
Deep neural networks present impressive performance, yet they cannot reliably estimate their predictive confidence, limiting their applicability in high-risk domains. We show that…
Continual Learning with Guarantees via Weight Interval Constraints
Maciej Wołczyk, Karol J. Piczak, Bartosz Wójcik +5
We introduce a new training paradigm that enforces interval constraints on neural network parameter space to control forgetting. Contemporary Continual Learning (CL) methods focus…