Adaptive Transform Coding for Semantic Compression

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Enttsel, Andriy, Corlay, Vincent
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910177337278464
author Enttsel, Andriy
Corlay, Vincent
author_facet Enttsel, Andriy
Corlay, Vincent
contents Visual data compression is shifting from human-centered reconstruction to machine-oriented representation coding. In this setting, an image is often mapped to a compact semantic embedding, which is then compressed and transmitted for downstream inference. We propose an adaptive transform-coding method for semantic-feature compression motivated by the conditional rate-distortion function of a Gaussian mixture model. The scheme uses mode-dependent transforms and quantizers selected according to the inferred source component, enabling more efficient coding of heterogeneous feature distributions. Evaluations on features from widely used vision backbones and foundation models show that the proposed method outperforms or is competitive with state-of-the-art neural compression methods while preserving flexibility and interpretability.
format Preprint
id arxiv_https___arxiv_org_abs_2604_26492
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Adaptive Transform Coding for Semantic Compression
Enttsel, Andriy
Corlay, Vincent
Image and Video Processing
Computer Vision and Pattern Recognition
Information Theory
Signal Processing
Visual data compression is shifting from human-centered reconstruction to machine-oriented representation coding. In this setting, an image is often mapped to a compact semantic embedding, which is then compressed and transmitted for downstream inference. We propose an adaptive transform-coding method for semantic-feature compression motivated by the conditional rate-distortion function of a Gaussian mixture model. The scheme uses mode-dependent transforms and quantizers selected according to the inferred source component, enabling more efficient coding of heterogeneous feature distributions. Evaluations on features from widely used vision backbones and foundation models show that the proposed method outperforms or is competitive with state-of-the-art neural compression methods while preserving flexibility and interpretability.
title Adaptive Transform Coding for Semantic Compression
topic Image and Video Processing
Computer Vision and Pattern Recognition
Information Theory
Signal Processing
url https://arxiv.org/abs/2604.26492