GAN- vs. JPEG2000 Image Compression for Distributed Automotive Perception: Higher Peak SNR Does Not Mean Better Semantic Segmentation

The high amount of sensors required for autonomous driving poses enormous challenges on the capacity of automotive bus systems. There is a need to understand tradeoffs between bitrate and perception performance. In this paper, we compare the image compression standards JPEG, JPEG2000, and WebP to a modern encoder/decoder image compression approach based on generative adversarial networks (GANs). We evaluate both the pure compression performance using typical metrics such as peak signal-to-noise ratio (PSNR), structural similarity (SSIM) and others, but also the performance of a subsequent perception function, namely a semantic segmentation (characterized by the mean intersection over union (mIoU) measure). Not surprisingly, for all investigated compression methods, a higher bitrate means better results in all investigated quality metrics. Interestingly, however, we show that the semantic segmentation mIoU of the GAN autoencoder in the highly relevant low-bitrate regime (at 0.0625 bit/pixel) is better by 3.9% absolute than JPEG2000, although the latter still is considerably better in terms of PSNR (5.91 dB difference). This effect can greatly be enlarged by training the semantic segmentation model with images originating from the decoder, so that the mIoU using the segmentation model trained by GAN reconstructions exceeds the use of the model trained with original images by almost 20% absolute. We conclude that distributed perception in future autonomous driving will most probably not provide a solution to the automotive bus capacity bottleneck by using standard compression schemes such as JPEG2000, but requires modern coding approaches, with the GAN encoder/decoder method being a promising candidate.

[1]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[2]  Xiaogang Wang,et al.  Pyramid Scene Parsing Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  David Minnen,et al.  Variable Rate Image Compression with Recurrent Neural Networks , 2015, ICLR.

[4]  Swami Sankaranarayanan,et al.  Learning from Synthetic Data: Addressing Domain Shift for Semantic Segmentation , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[5]  George Papandreou,et al.  Rethinking Atrous Convolution for Semantic Image Segmentation , 2017, ArXiv.

[6]  Raymond Y. K. Lau,et al.  Least Squares Generative Adversarial Networks , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[7]  Camille Couprie,et al.  Semantic Segmentation using Adversarial Networks , 2016, NIPS 2016.

[8]  Sepp Hochreiter,et al.  GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium , 2017, NIPS.

[9]  Luc Van Gool,et al.  The Pascal Visual Object Classes Challenge: A Retrospective , 2014, International Journal of Computer Vision.

[10]  Xiaohua Zhai,et al.  The GAN Landscape: Losses, Architectures, Regularization, and Normalization , 2018, ArXiv.

[11]  Navdeep Jaitly,et al.  Adversarial Autoencoders , 2015, ArXiv.

[12]  Sebastian Ramos,et al.  The Cityscapes Dataset for Semantic Urban Scene Understanding , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Eric P. Xing,et al.  Semantic-aware Grad-GAN for Virtual-to-Real Urban Scene Adaption , 2018, BMVC.

[14]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[15]  Yoshua Bengio,et al.  Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation , 2013, ArXiv.

[16]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[17]  Léon Bottou,et al.  Wasserstein GAN , 2017, ArXiv.

[18]  Lubomir D. Bourdev,et al.  Real-Time Adaptive Image Compression , 2017, ICML.

[19]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[21]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[22]  Yochai Blau,et al.  The Perception-Distortion Tradeoff , 2017, CVPR.

[23]  Alexandros G. Dimakis,et al.  The Robust Manifold Defense: Adversarial Training using Generative Models , 2017, ArXiv.

[24]  Anton van den Hengel,et al.  Wider or Deeper: Revisiting the ResNet Model for Visual Recognition , 2016, Pattern Recognit..

[25]  Luc Van Gool,et al.  Generative Adversarial Networks for Extreme Learned Image Compression , 2018, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[26]  Ali Borji,et al.  Pros and Cons of GAN Evaluation Measures , 2018, Comput. Vis. Image Underst..

[27]  Tomas Pfister,et al.  Learning from Simulated and Unsupervised Images through Adversarial Training , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Lorenzo Porzi,et al.  In-place Activated BatchNorm for Memory-Optimized Training of DNNs , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[29]  Vladlen Koltun,et al.  Multi-Scale Context Aggregation by Dilated Convolutions , 2015, ICLR.

[30]  David Salomon,et al.  Data Compression: The Complete Reference , 2006 .

[31]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

[32]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[33]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[34]  Zhou Wang,et al.  Multi-scale structural similarity for image quality assessment , 2003 .

[35]  Mark Sandler,et al.  MobileNetV2: Inverted Residuals and Linear Bottlenecks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[36]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[37]  George Papandreou,et al.  Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation , 2018, ECCV.

[38]  Rama Chellappa,et al.  Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models , 2018, ICLR.

[39]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[40]  Eduardo Romera,et al.  ERFNet: Efficient Residual Factorized ConvNet for Real-Time Semantic Segmentation , 2018, IEEE Transactions on Intelligent Transportation Systems.

[41]  David Berthelot,et al.  BEGAN: Boundary Equilibrium Generative Adversarial Networks , 2017, ArXiv.

[42]  Stefano Ermon,et al.  Generative Adversarial Imitation Learning , 2016, NIPS.

[43]  Valero Laparra,et al.  End-to-end Optimized Image Compression , 2016, ICLR.

[44]  拓海 杉山,et al.  “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告 , 2017 .

[45]  Yann LeCun,et al.  Energy-based Generative Adversarial Network , 2016, ICLR.

[46]  Jan Kautz,et al.  High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[47]  Mingyan Liu,et al.  Generating Adversarial Examples with Adversarial Networks , 2018, IJCAI.

[48]  Fabio Galasso,et al.  Adversarial Network Compression , 2018, ECCV Workshops.

[49]  Iasonas Kokkinos,et al.  DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[50]  Nir Shavit,et al.  Generative Compression , 2017, 2018 Picture Coding Symposium (PCS).

[51]  Lucas Theis,et al.  Lossy Image Compression with Compressive Autoencoders , 2017, ICLR.