让图像压缩更懂机器任务，提升模型分析效果
Learning-Based Image Compression for Machines
- 在预训练压缩模型上微调，融入下游视觉任务需求
- 压缩后图像仍能保持关键特征，支持准确的视觉识别
- 适合需要高效存储与推理的AI系统开发者
基于学习的图像压缩技术虽已超越传统方法，但在机器学习流程中尚未广泛应用，主要因缺乏标准化及未能保留对任务关键的显著特征。近年来，解压环节被忽视，研究重心转向图像在机器学习分析中的实用性。因此，亟需能保留关键信息的压缩管道。本文基于现有学习型压缩技术，提出多种微调和增强预训练编码管道的方法，并评估了压缩后图像在各类视觉任务中的表现，验证了其在保持压缩效率的同时有效支撑下游任务的可行性。
原文摘要 · Abstract (English)
While learning based compression techniques for images have outperformed traditional methods, they have not been widely adopted in machine learning pipelines. This is largely due to lack of standardization and lack of retention of salient features needed for such tasks. Decompression of images have taken a back seat in recent years while the focus has shifted to an image's utility in performing machine learning based analysis on top of them. Thus the demand for compression pipelines that incorporate such features from images has become ever present. The methods outlined in the report build on the recent work done on learning based image compression techniques to incorporate downstream tasks in them. We propose various methods of finetuning and enhancing different parts of pretrained compression encoding pipeline and present the results of our investigation regarding the performance of vision tasks using compression based pipelines.
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。