Learning based Facial Image Compression with Semantic Fidelity Metric

Abstract

Surveillance and security scenarios usually require high efficient facial image compression scheme for face recognition and identification. While either traditional general image codecs or special facial image compression schemes only heuristically refine codec separately according to face verification accuracy metric. We propose a Learning based Facial Image Compression (LFIC) framework with a novel Regionally Adaptive Pooling (RAP) module whose parameters can be automatically optimized according to gradient feedback from an integrated hybrid semantic fidelity metric, including a successfully exploration to apply Generative Adversarial Network (GAN) as metric directly in image compression scheme. The experimental results verify the framework's efficiency by demonstrating performance improvement of 71.41%, 48.28% and 52.67% bitrate saving separately over JPEG2000, WebP and neural network-based codecs under the same face verification accuracy distortion metric. We also evaluate LFIC's superior performance gain compared with latest specific facial image codecs. Visual experiments also show some interesting insight on how LFIC can automatically capture the information in critical areas based on semantic distortion metrics for optimized compression, which is quite different from the heuristic way of optimization in traditional image compression algorithms.

arXiv commentAccepted by Neurocomputing

References in corpus (7)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
• Variational image compression with a scale hyperprior
• End-to-end Optimized Image Compression
• Learning for Video Compression
• Guetzli: Perceptually Guided JPEG Encoder
• Sparse Multi-layer Image Approximation: Facial Image Compression

Cited by in corpus (11)

• Deep Learning-Based Video Coding: A Review and A Case Study
• Learning for Video Compression
• Recent Standard Development Activities on Video Coding for Machines
• Cross Modal Compression: Towards Human-comprehensible Semantic Compression
• Learned Block-based Hybrid Image Compression
• 3-D Context Entropy Model for Improved Practical Image Compression
• Task-driven Semantic Coding via Reinforcement Learning
• Visual Analysis Motivated Rate-Distortion Model for Image Coding
• End-to-End Image Compression with Probabilistic Decoding
• Reinforced Bit Allocation under Task-Driven Semantic Distortion Metrics
• Multi-scale Grouped Dense Network for VVC Intra Coding