arXiv (Cornell University) · 2018 · 72 citations · 27 references
ComputingComputer ScienceComputational ArtComputer VisionDigital RenderingDeep LearningGenerative ModelingImage SynthesisObject RecognitionPhotorealistic RenderingTransfer LearningAdversarial Domain AdaptationCovariate ShiftDomain AdaptationDomain Adaptation For Semantic SegmentationImage-to-image TranslationNeural Style TransferStyle TransferStylization
Deep neural networks have largely failed to effectively utilize synthetic data when applied to real images due to the covariate shift problem. In this paper, we show that by applying a straightforward modification to an existing photorealistic style transfer algorithm, we achieve state-of-the-art synthetic-to-real domain adaptation results. We conduct extensive experimental validations on four synthetic-to-real tasks for semantic segmentation and object detection, and show that our approach exceeds the performance of any current state-of-the-art GAN-based image translation approach as measured by segmentation and object detection metrics. Furthermore we offer a distance based analysis of our method which shows a dramatic reduction in Frechet Inception distance between the source and target domains, offering a quantitative metric that demonstrates the effectiveness of our algorithm in bridging the synthetic-to-real gap.
27
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
Rethinking the Inception Architecture for Computer Vision
Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe et al. · 2016 · 30.9K citations
Are we ready for autonomous driving? The KITTI vision benchmark suite
Andreas Geiger, P Lenz, R. Urtasun · 2012 · 14.4K citations
Rethinking Atrous Convolution for Semantic Image Segmentation
Liang-Chieh Chen, George Papandreou, Florian Schroff et al. · arXiv (Cornell University) · 2017 · 7.5K citations · Full text