Search Results for author: Łukasz Treszczotko

Found 2 papers, 0 papers with code

Automated Channel Pruning with Learned Importance

no code implementations29 Sep 2021 Łukasz Treszczotko, Pawel Kubik

The framework contains 1) an automatic channel detection algorithm that groups the interdependent blocks of channels; 2) a non-iterative pruning algorithm that learns channel importance directly from feature maps while masking the coupled computational blocks using Gumbel-Softmax sampling and 3) a hierarchical knowledge distillation approach to fine-tune the pruned neural networks.

Image Denoising Knowledge Distillation +1

Superkernel Neural Architecture Search for Image Denoising

no code implementations19 Apr 2020 Marcin Możejko, Tomasz Latkowski, Łukasz Treszczotko, Michał Szafraniuk, Krzysztof Trojanowski

Recent advancements in Neural Architecture Search(NAS) resulted in finding new state-of-the-art Artificial Neural Network (ANN) solutions for tasks like image classification, object detection, or semantic segmentation without substantial human supervision.

Image Classification Image Denoising +7

Cannot find the paper you are looking for? You can Submit a new open access paper.