Online Meta Adaptation for Variable-Rate Learned Image Compression

This work addresses two major issues of end-to-end learned image compression (LIC) based on deep neural networks: variable-rate learning where separate networks are required to generate compressed images with varying qualities, and the train-test mismatch between differentiable approximate quantization and true hard quantization. We introduce an online meta-learning (OML) setting for LIC, which combines ideas from meta learning and online learning in the conditional variational auto-encoder (CVAE) framework. By treating the conditional variables as meta parameters and treating the generated conditional features as meta priors, the desired reconstruction can be controlled by the meta parameters to accommodate compression with variable qualities. The online learning framework is used to update the meta parameters so that the conditional reconstruction is adaptively tuned for the current image. Through the OML mechanism, the meta parameters can be effectively updated through SGD. The conditional reconstruction is directly based on the quantized latent representation in the decoder network, and therefore helps to bridge the gap between the training estimation and true quantized latent distribution. Experiments demonstrate that our OML approach can be flexibly applied to different state-of-the-art LIC methods to achieve additional performance improvements with little computation and transmission overhead.

[1]  Akshay Pushparaja,et al.  CompressAI: a PyTorch library and evaluation platform for end-to-end compression research , 2020, ArXiv.

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

[3]  Eirikur Agustsson,et al.  Universally Quantized Neural Compression , 2020, NeurIPS.

[4]  Nam Ik Cho,et al.  Meta-Transfer Learning for Zero-Shot Super-Resolution , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Yoram Singer,et al.  Adaptive Subgradient Methods for Online Learning and Stochastic Optimization , 2011, J. Mach. Learn. Res..

[6]  David Minnen,et al.  Variational image compression with a scale hyperprior , 2018, ICLR.

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

[8]  David Minnen,et al.  Full Resolution Image Compression with Recurrent Neural Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Zhizheng Zhang,et al.  3-D Context Entropy Model for Improved Practical Image Compression , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[10]  Steven C. H. Hoi,et al.  Online Deep Learning: Learning Deep Neural Networks on the Fly , 2017, IJCAI.

[11]  Andre Wibisono,et al.  Streaming Variational Bayes , 2013, NIPS.

[12]  Sergey Levine,et al.  Online Meta-Learning , 2019, ICML.

[13]  Jungwon Lee,et al.  Variable Rate Deep Image Compression With a Conditional Autoencoder , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[14]  Sergey Levine,et al.  Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL , 2018, ICLR.

[15]  Pieter Abbeel,et al.  A Simple Neural Attentive Meta-Learner , 2017, ICLR.

[16]  Jooyoung Lee,et al.  Context-adaptive Entropy Model for End-to-end Optimized Image Compression , 2018, ICLR.

[17]  Gregory K. Wallace,et al.  The JPEG still picture compression standard , 1991, CACM.

[18]  Sergey Levine,et al.  Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks , 2017, ICML.

[19]  David Minnen,et al.  Joint Autoregressive and Hierarchical Priors for Learned Image Compression , 2018, NeurIPS.

[20]  Luc Van Gool,et al.  Conditional Probability Models for Deep Image Compression , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[21]  Joost van de Weijer,et al.  Variable Rate Deep Image Compression With Modulated Autoencoder , 2019, IEEE Signal Processing Letters.

[22]  Gary J. Sullivan,et al.  Overview of the High Efficiency Video Coding (HEVC) Standard , 2012, IEEE Transactions on Circuits and Systems for Video Technology.

[23]  Richard S. Zemel,et al.  Prototypical Networks for Few-shot Learning , 2017, NIPS.

[24]  Amos J. Storkey,et al.  How to train your MAML , 2018, ICLR.

[25]  Songnan Li,et al.  PnG: Micro-structured Prune-and-Grow Networks for Flexible Image Restoration , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[26]  Brian Kulis,et al.  Substitutional Neural Image Compression , 2021, 2022 Picture Coding Symposium (PCS).

[27]  Edwin Pan,et al.  MetaHDR: Model-Agnostic Meta-Learning for HDR Image Reconstruction , 2021, ArXiv.

[28]  Sergey Levine,et al.  Learning to Adapt in Dynamic, Real-World Environments through Meta-Reinforcement Learning , 2018, ICLR.

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

[30]  Bindhu,et al.  Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules , 2021, December 2020.

[31]  Yan Wang,et al.  Checkerboard Context Model for Efficient Learned Image Compression , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[32]  Majid Rabbani,et al.  An overview of the JPEG 2000 still image compression standard , 2002, Signal Process. Image Commun..