Slimmable Video Codec
Neural video compression has emerged as a novel paradigm combining trainable multilayer neural networks and machine learning, achieving competitive rate-distortion (RD) performances, but still remaining impractical due to heavy neural architectures, with large memory and computational demands. In addition, models are usually optimized for a single RD tradeoff. Recent slimmable image codecs can dynamically adjust their model capacity to gracefully reduce the memory and computation requirements, without harming RD performance. In this paper we propose a slimmable video codec (SlimVC), by integrating a slimmable temporal entropy model in a slimmable autoencoder. Despite a significantly more complex architecture, we show that slimming remains a powerful mechanism to control rate, memory footprint, computational cost and latency, all being important requirements for practical video compression.
Code (0)
등록된 구현이 없습니다.
Tasks
Video CompressionSimilar Papers 제목 키워드 기반
Complexity-Guided Slimmable Decoder for Efficient Deep Video Compression
In this work, we propose the complexity-guided slimmable decoder (cgSlimDecoder) in combination with skip-adaptive entropy coding (SaEC) for efficient deep video compression. Specifically, given the target complexity…
DecoderMotion CompensationVideo CompressionSlimmable Compressive Autoencoders for Practical Neural Image Compression
Neural image compression leverages deep neural networks to outperform traditional image codecs in rate-distortion performance. However, the resulting models are also heavy, computationally demanding and generally optimiz…
Image CompressionFull Reference Video Quality Assessment for Machine Learning-Based Video Codecs
Machine learning-based video codecs have made significant progress in the past few years. A critical area in the development of ML-based video codecs is an accurate evaluation metric that does not require an expensive an…
Video Quality AssessmentUniversally Slimmable Networks and Improved Training Techniques
Slimmable networks are a family of neural networks that can instantly adjust the runtime width. The width can be chosen from a predefined widths set to adaptively optimize accuracy-efficiency trade-offs at runtime. In th…
Deep Reinforcement LearningImage Super-ResolutionReinforcement LearningSuper-ResolutionSmall-footprint slimmable networks for keyword spotting
In this work, we present Slimmable Neural Networks applied to the problem of small-footprint keyword spotting. We show that slimmable neural networks allow us to create super-nets from Convolutioanl Neural Networks and T…
Keyword SpottingSmall-Footprint Keyword Spotting