Flexible Variable-Rate Image Feature Compression for Edge-Cloud Systems

Abstract

Feature compression is a promising direction for coding for machines. Existing methods have made substantial progress, but they require designing and training separate neural network models to meet different specifications of compression rate, performance accuracy and computational complexity. In this paper, a flexible variable-rate feature compression method is presented that can operate on a range of rates by introducing a rate control parameter as an input to the neural network model. By compressing different intermediate features of a pre-trained vision task model, the proposed method can scale the encoding complexity without changing the overall size of the model. The proposed method is more flexible than existing baselines, at the same time outperforming them in terms of the three-way trade-off between feature compression rate, vision task accuracy, and encoding complexity. We have made the source code available at https://github.com/adnan-hossain/var_feat_comp.git.

arXiv comment6 pages, 7 figures, 1 table, International Conference on Multimedia and Expo Workshops 2023

References in corpus (10)

• End-to-end Optimized Image Compression
• Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations
• Context-adaptive Entropy Model for End-to-end Optimized Image Compression
• Neural Image Compression for Gigapixel Histopathology Image Analysis
• Scalable Image Coding for Humans and Machines
• Asymmetric numeral systems: entropy coding combining speed of Huffman coding with compression rate of arithmetic coding
• QARV: Quantization-Aware ResNet VAE for Lossy Image Compression
• Supervised Compression for Resource-Constrained Edge Computing Systems
• Lightweight compression of neural network feature tensors for collaborative intelligence
• Lightweight Compression of Intermediate Neural Network Features for Collaborative Intelligence