Saved in:
Bibliographic Details
Main Authors: Shen, Ruiqi, Wu, Haotian, Zhang, Wenjing, Hu, Jiangjing, Gunduz, Deniz
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.05925
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914026519265280
author Shen, Ruiqi
Wu, Haotian
Zhang, Wenjing
Hu, Jiangjing
Gunduz, Deniz
author_facet Shen, Ruiqi
Wu, Haotian
Zhang, Wenjing
Hu, Jiangjing
Gunduz, Deniz
contents Recent deep learning-based methods for lossy image compression achieve competitive rate-distortion performance through extensive end-to-end training and advanced architectures. However, emerging applications increasingly prioritize semantic preservation over pixel-level reconstruction and demand robust performance across diverse data distributions and downstream tasks. These challenges call for advanced semantic compression paradigms. Motivated by the zero-shot and representational capabilities of multimodal foundation models, we propose a novel semantic compression method based on the contrastive language-image pretraining (CLIP) model. Rather than compressing images for reconstruction, we propose compressing the CLIP feature embeddings into minimal bits while preserving semantic information across different tasks. Experiments show that our method maintains semantic integrity across benchmark datasets, achieving an average bit rate of approximately 2-3* 10(-3) bits per pixel. This is less than 5% of the bitrate required by mainstream image compression approaches for comparable performance. Remarkably, even under extreme compression, the proposed approach exhibits zero-shot robustness across diverse data distributions and downstream tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2509_05925
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Compression Beyond Pixels: Semantic Compression with Multimodal Foundation Models
Shen, Ruiqi
Wu, Haotian
Zhang, Wenjing
Hu, Jiangjing
Gunduz, Deniz
Computer Vision and Pattern Recognition
Information Theory
Recent deep learning-based methods for lossy image compression achieve competitive rate-distortion performance through extensive end-to-end training and advanced architectures. However, emerging applications increasingly prioritize semantic preservation over pixel-level reconstruction and demand robust performance across diverse data distributions and downstream tasks. These challenges call for advanced semantic compression paradigms. Motivated by the zero-shot and representational capabilities of multimodal foundation models, we propose a novel semantic compression method based on the contrastive language-image pretraining (CLIP) model. Rather than compressing images for reconstruction, we propose compressing the CLIP feature embeddings into minimal bits while preserving semantic information across different tasks. Experiments show that our method maintains semantic integrity across benchmark datasets, achieving an average bit rate of approximately 2-3* 10(-3) bits per pixel. This is less than 5% of the bitrate required by mainstream image compression approaches for comparable performance. Remarkably, even under extreme compression, the proposed approach exhibits zero-shot robustness across diverse data distributions and downstream tasks.
title Compression Beyond Pixels: Semantic Compression with Multimodal Foundation Models
topic Computer Vision and Pattern Recognition
Information Theory
url https://arxiv.org/abs/2509.05925