IVAICVITLGMar 15, 2024

Learning on JPEG-LDPC Compressed Images: Classifying with Syndromes

arXiv:2403.10202v11 citationsh-index: 10EUSIPCO
Originality Incremental advance
AI Analysis

This addresses the need for time-efficient inference in goal-oriented communications, though it is incremental as it adapts existing LDPC codes and GRU models to a specific compression-learning scenario.

The paper tackles the problem of performing image classification directly on compressed data without decompression, proposing to use LDPC codes instead of conventional entropic coding, and shows that this approach outperforms Huffman and Arithmetic coding while requiring a smaller model.

In goal-oriented communications, the objective of the receiver is often to apply a Deep-Learning model, rather than reconstructing the original data. In this context, direct learning over compressed data, without any prior decoding, holds promise for enhancing the time-efficient execution of inference models at the receiver. However, conventional entropic-coding methods like Huffman and Arithmetic break data structure, rendering them unsuitable for learning without decoding. In this paper, we propose an alternative approach in which entropic coding is realized with Low-Density Parity Check (LDPC) codes. We hypothesize that Deep Learning models can more effectively exploit the internal code structure of LDPC codes. At the receiver, we leverage a specific class of Recurrent Neural Networks (RNNs), specifically Gated Recurrent Unit (GRU), trained for image classification. Our numerical results indicate that classification based on LDPC-coded bit-planes surpasses Huffman and Arithmetic coding, while necessitating a significantly smaller learning model. This demonstrates the efficiency of classification directly from LDPC-coded data, eliminating the need for any form of decompression, even partial, prior to applying the learning model.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes