Identity Preserving Loss for Learned Image Compression

TL;DR

This paper introduces an end-to-end image compression framework that preserves identity features, achieving higher compression ratios than standard methods while maintaining recognition accuracy, especially for face images, without needing downstream task fine-tuning.

Contribution

The work proposes a novel Identity Preserving Reconstruction loss for learned image compression that retains domain-specific features and is robust across different recognition models.

Findings

Achieves ~38-42% of CRF-23 HEVC compression BPP with maintained recognition accuracy.

Learns to retain facial features while sacrificing background details.

Robust to changes in downstream recognition model architectures.

Abstract

Deep learning model inference on embedded devices is challenging due to the limited availability of computation resources. A popular alternative is to perform model inference on the cloud, which requires transmitting images from the embedded device to the cloud. Image compression techniques are commonly employed in such cloud-based architectures to reduce transmission latency over low bandwidth networks. This work proposes an end-to-end image compression framework that learns domain-specific features to achieve higher compression ratios than standard HEVC/JPEG compression techniques while maintaining accuracy on downstream tasks (e.g., recognition). Our framework does not require fine-tuning of the downstream task, which allows us to drop-in any off-the-shelf downstream task model without retraining. We choose faces as an application domain due to the ready availability of datasets and off-the-shelf recognition models as representative downstream tasks. We present a novel Identity Preserving Reconstruction (IPR) loss function which achieves Bits-Per-Pixel (BPP) values that are ~38% and ~42% of CRF-23 HEVC compression for LFW (low-resolution) and CelebA-HQ (high-resolution) datasets, respectively, while maintaining parity in recognition accuracy. The superior compression ratio is achieved as the model learns to retain the domain-specific features (e.g., facial features) while sacrificing details in the background. Furthermore, images reconstructed by our proposed compression model are robust to changes in downstream model architectures. We show at-par recognition performance on the LFW dataset with an unseen recognition model while retaining a lower BPP value of ~38% of CRF-23 HEVC compression.