Calibrated Adversarial Refinement for Stochastic Semantic Segmentation

3 code implementations • ICCV 2021 • Elias Kassapis, Georgi Dikov, Deepak K. Gupta, Cedric Nugteren

To this end, we propose a novel two-stage, cascaded approach for calibrated adversarial refinement: (i) a standard segmentation network is trained with categorical cross entropy to predict a pixelwise probability distribution over semantic classes and (ii) an adversarially trained stochastic network is used to model the inter-pixel correlations to refine the output of the first network into coherent samples.

Semantic Segmentation valid

EL-GAN: Embedding Loss Driven Generative Adversarial Networks for Lane Detection

no code implementations • 14 Jun 2018 • Mohsen Ghafoorian, Cedric Nugteren, Nóra Baka, Olaf Booij, Michael Hofmann

Convolutional neural networks have been successfully applied to semantic segmentation problems.

Lane Detection Segmentation +1

CLBlast: A Tuned OpenCL BLAS Library

1 code implementation • 12 May 2017 • Cedric Nugteren

This work introduces CLBlast, an open-source BLAS library providing optimized OpenCL routines to accelerate dense linear algebra for a wide variety of devices.

CLTune: A Generic Auto-Tuner for OpenCL Kernels

2 code implementations • 19 Mar 2017 • Cedric Nugteren, Valeriu Codreanu

For matrix-multiplication, we use CLTune to explore a parameter space of more than two-hundred thousand configurations, we show the need for device-specific tuning, and outperform the clBLAS library on NVIDIA, AMD and Intel GPUs.

Rolling Shutter Correction