一个编码器搞定多种压缩需求，省去反复训练。
Universal Representations for Classification-enhanced Lossy Compression
- 设计通用编码器，统一处理不同压缩与分类目标。
- 在MNIST上性能接近专用编码器，损失极小。
- 跨任务复用编码器时，压缩失真会显著增加。
在有损压缩中，传统设计以压缩率与重建失真之间的权衡为核心。近期研究引入了率-失真-感知（RDP）和率-失真-分类（RDC）框架，将感知质量或分类准确率纳入评价维度。本文探索通用表示，即开发单一编码器以支持多种解码目标，适应不同失真和分类（或感知）约束。该方法避免为每种权衡点重新训练编码器。在MNIST数据集上的实验表明，通用编码器在感知图像压缩任务中性能仅轻微下降，与[23]结果一致。然而，在RDC设置下，使用为特定分类-失真权衡优化的编码器应用于其他点时，会带来显著的失真代价。
原文摘要 · Abstract (English)
In lossy compression, the classical tradeoff between compression rate and reconstruction distortion has traditionally guided algorithm design. However, Blau and Michaeli [5] introduced a generalized framework, known as the rate-distortion-perception (RDP) function, incorporating perceptual quality as an additional dimension of evaluation. More recently, the rate-distortion-classification (RDC) function was investigated in [19], evaluating compression performance by considering classification accuracy alongside distortion. In this paper, we explore universal representations, where a single encoder is developed to achieve multiple decoding objectives across various distortion and classification (or perception) constraints. This universality avoids retraining encoders for each specific operating point within these tradeoffs. Our experimental validation on the MNIST dataset indicates that a universal encoder incurs only minimal performance degradation compared to individually optimized encoders for perceptual image compression tasks, aligning with prior results from [23]. Nonetheless, we also identify that in the RDC setting, reusing an encoder optimized for one specific classification-distortion tradeoff leads to a significant distortion penalty when applied to alternative points.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。