Zobrazeno 1 - 10
of 22
pro vyhledávání: '"Wojna, Zbigniew"'
Recent advancements in computer vision promise to automate medical image analysis. Rheumatoid arthritis is an autoimmune disease that would profit from computer-based diagnosis, as there are no direct markers known, and doctors have to rely on manual
Externí odkaz:
http://arxiv.org/abs/2104.13915
This work presents a method for reducing memory consumption to a constant complexity when training deep neural networks. The algorithm is based on the more biologically plausible alternatives of the backpropagation (BP): direct feedback alignment (DF
Externí odkaz:
http://arxiv.org/abs/2012.11745
In this paper, we present augmentation inside the network, a method that simulates data augmentation techniques for computer vision problems on intermediate features of a convolutional neural network. We perform these transformations, changing the da
Externí odkaz:
http://arxiv.org/abs/2012.10769
Autor:
Wojna, Zbigniew, Maziarz, Krzysztof, Jocz, Łukasz, Pałuba, Robert, Kozikowski, Robert, Kokkinos, Iasonas
We address six different classification tasks related to fine-grained building attributes: construction type, number of floors, pitch and geometry of the roof, facade material, and occupancy class. Tackling such a remote building analysis problem bec
Externí odkaz:
http://arxiv.org/abs/2008.10041
Autor:
Morrell, Stephen, Wojna, Zbigniew, Khoo, Can Son, Ourselin, Sebastien, Iglesias, Juan Eugenio
State-of-the-art deep learning methods for image processing are evolving into increasingly complex meta-architectures with a growing number of modules. Among them, region-based fully convolutional networks (R-FCN) and deformable convolutional nets (D
Externí odkaz:
http://arxiv.org/abs/1902.07323
In recent years, object detection has experienced impressive progress. Despite these improvements, there is still a significant gap in the performance between the detection of small and large objects. We analyze the current state-of-the-art model, Ma
Externí odkaz:
http://arxiv.org/abs/1902.07296
Autor:
Wojna, Zbigniew, Ferrari, Vittorio, Guadarrama, Sergio, Silberman, Nathan, Chen, Liang-Chieh, Fathi, Alireza, Uijlings, Jasper
Many machine vision applications, such as semantic segmentation and depth prediction, require predictions for every pixel of the input image. Models for such problems usually consist of encoders which decrease spatial resolution while learning a high
Externí odkaz:
http://arxiv.org/abs/1707.05847
Autor:
Wojna, Zbigniew, Gorban, Alex, Lee, Dar-Shyang, Murphy, Kevin, Yu, Qian, Li, Yeqing, Ibarz, Julian
We present a neural network model - based on CNNs, RNNs and a novel attention mechanism - which achieves 84.2% accuracy on the challenging French Street Name Signs (FSNS) dataset, significantly outperforming the previous state of the art (Smith'16),
Externí odkaz:
http://arxiv.org/abs/1704.03549
Autor:
Fathi, Alireza, Wojna, Zbigniew, Rathod, Vivek, Wang, Peng, Song, Hyun Oh, Guadarrama, Sergio, Murphy, Kevin P.
We propose a new method for semantic instance segmentation, by first computing how likely two pixels are to belong to the same object, and then by grouping similar pixels together. Our similarity metric is based on a deep, fully convolutional embeddi
Externí odkaz:
http://arxiv.org/abs/1703.10277
Autor:
Huang, Jonathan, Rathod, Vivek, Sun, Chen, Zhu, Menglong, Korattikara, Anoop, Fathi, Alireza, Fischer, Ian, Wojna, Zbigniew, Song, Yang, Guadarrama, Sergio, Murphy, Kevin
The goal of this paper is to serve as a guide for selecting a detection architecture that achieves the right speed/memory/accuracy balance for a given application and platform. To this end, we investigate various ways to trade accuracy for speed and
Externí odkaz:
http://arxiv.org/abs/1611.10012