Werner Bailer | Joanneum Research, Graz | Friday, June 25, 2021 | 10:00 (CET, 08:00 UTC) | online
Artificial neural networks have been adopted for a broad range of tasks in multimedia analysis and processing, such as visual and acoustic classification, extraction of multimedia descriptors or image and video coding. The trained neural networks for these applications contain a large number of parameters (weights), resulting in a considerable size. Thus, transferring them to a number of clients using them in applications (e.g., mobile phones, smart cameras) benefits from a compressed representation of neural networks.
MPEG Neural Network Coding and Representation is the first international standard for efficient compression of neural networks (NNs). The standard is designed as a toolbox of compression methods, which can be used to create coding pipelines. It can be either used as an independent coding framework (with its own bitstream format) or together with external neural network formats and frameworks. For providing the highest degree of flexibility, the network compression methods operate per parameter tensor in order to always ensure proper decoding, even if no structure information is provided. The standard contains compression-efficient quantization and an arithmetic coding scheme (DeepCABAC) as core encoding and decoding technologies, as well as neural network parameter pre-processing methods like sparsification, pruning, low-rank decomposition, unification, local scaling and batch norm folding. NNR achieves a compression efficiency of more than 97% for transparent coding cases, i.e. without degrading classification quality, such as top-1 or top-5 accuracies.
This talk presents an overview of the context, technical features and characteristics of NN coding standard, and discusses ongoing topics such as incremental neural network representation.
Werner Bailer is a Key Researcher at DIGITAL – Institute for Information and Communication Technologies at JOANNEUM RESEARCH in Graz, Austria. He received a degree in Media Technology and Design in 2002 for his diploma thesis on motion estimation and segmentation for film/video standards conversion. His research interests include audiovisual content analysis, multimedia retrieval and machine learning. He regularly contributes to standardization, among others in MPEG, where he co-chairs the ad-hoc group on neural network compression.