Identity Preserving Loss for Learned Image Compression

by   Jiuhong Xiao, et al.

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 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


page 1

page 4

page 8


Are Visual Recognition Models Robust to Image Compression?

Reducing the data footprint of visual content via image compression is e...

Pragmatic Image Compression for Human-in-the-Loop Decision-Making

Standard lossy image compression algorithms aim to preserve an image's a...

Prompt-ICM: A Unified Framework towards Image Coding for Machines with Task-driven Prompts

Image coding for machines (ICM) aims to compress images to support downs...

Leveraging Domain Knowledge using Machine Learning for Image Compression in Internet-of-Things

The emergent ecosystems of intelligent edge devices in diverse Internet ...

Dynamic-Deep: ECG Task-Aware Compression

Monitoring medical data, e.g., Electrocardiogram (ECG) signals, is a com...

Semantic-assisted image compression

Conventional image compression methods typically aim at pixel-level cons...

Adapting JPEG XS gains and priorities to tasks and contents

Most current research in the domain of image compression focuses solely ...

Please sign up or login with your details

Forgot password? Click here to reset