一次训练让压缩模型同时服务多个机器视觉任务
All-in-One Transferring Image Compression from Human Perception to Multi-Machine Perception
- 设计异构适配结构，共享编码器、分任务解码器
- 在PASCAL-Context和NYUD-V2上优于全微调与参数高效方法
- 适合需要多任务统一压缩的工业级视觉系统
将学习型图像压缩（LIC）模型从人类感知高效迁移到机器感知，是视觉表征学习中的新兴挑战。现有方法通常以单任务方式适应下游任务，效率低、缺乏任务间交互，且产生多个专用比特流。本文提出一种多任务适配框架，通过统一模型与单一训练过程，将预训练基础编解码器迁移至多个机器视觉任务。为此，设计了非对称适配架构：任务无关的编码器适配与任务特定的解码器适配；并引入两种特征传播模块，促进任务间与尺度间特征表示学习。在PASCAL-Context和NYUD-V2数据集上的实验表明，该方法优于全微调及多种参数高效微调（PEFT）基线。代码将开源。
原文摘要 · Abstract (English)
Efficiently transferring Learned Image Compression (LIC) model from human perception to machine perception is an emerging challenge in vision-centric representation learning. Existing approaches typically adapt LIC to downstream tasks in a single-task manner, which is inefficient, lacks task interaction, and results in multiple task-specific bitstreams. In this paper, we propose a multi-task adaptation framework that enables transferring a pre-trained base codec to multiple machine vision tasks through a unified model and a single training process. To achieve this, we design an asymmetric adaptation architecture consisting of a task-agnostic encoder adaptation and task-specific decoder adaptation. Furthermore, we introduce two feature propagation modules to facilitate inter-task and inter-scale feature represenation learning. Experiments on PASCAL-Context and NYUD-V2 dataset demonstrate that our method outperforms both Fully Fine-Tuned and other Parameter Efficient Fine-Tuned (PEFT) baselines. Code will be released.
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。