为机器视觉设计可渐进传输的图像压缩方法，支持动态调整解码质量。
Progressive Learned Image Compression for Machine Perception
- 基于三元平面编码构建渐进式压缩架构，支持多级解码质量。
- 在低比特率下仍保持强下游分类性能，实现高效自适应传输。
- 适合需要实时调整解码精度的机器感知系统部署。
近年来，学习型图像编码器已从人类感知扩展至机器感知。然而，具备细粒度可扩展性（FGS）的渐进式图像压缩——即通过单一码流在多个质量级别上解码——在面向机器的编码中仍属空白。本文提出PICM-Net，一种基于三元平面编码的面向机器感知的渐进式学习图像压缩编码器。从面向人类的编码器出发，通过空间-频率调制适配器（SFMA）、超合成低秩适配器（HSLoRA）和渐进解码感知训练进行机器感知适配，并分析任务驱动的调整如何改变符号优先级以支持渐进传输。为进一步支持实际部署，引入自适应解码控制器，可在推理时动态决定所需解码级别，仅在当前适配度不足以达到目标置信度时请求额外比特。大量实验表明，PICM-Net在保持强大下游分类性能的同时，实现了高效且自适应的渐进传输。代码已开源：https://github.com/kjungwoo03/PICM-Net。
原文摘要 · Abstract (English)
Recent advances in learned image codecs have extended from human perception toward machine perception However, progressive image compression with fine granular scalability (FGS)-which enables decoding a single bitstream at multiple quality levels-remains unexplored for machine-oriented codecs. In this work, we propose PICM-Net, a progressive learned image compression codec for machine perception built on trit-plane coding. Starting from a human-oriented codec, we adapt it for machine perception via a spatial-frequency modulation adapter (SFMA), a hyper-synthesis low-rank adapter (HSLoRA), and progressive decoding-aware training, and analyze how task-driven adaptation alters symbol prioritization for progressive transmission. To further support real-world deployment, we introduce an adaptive decoding controller that dynamically determines the necessary decoding level at inference time, requesting additional bits only when the current suitability is insufficient for the desired confidence level. Extensive experiments demonstrate that PICM-Net achieves efficient and adaptive progressive transmission while maintaining strong downstream classification performance. Our code is available at https://github.com/kjungwoo03/PICM-Net.
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。