论文标题
搜索可控的图像恢复网络
Searching for Controllable Image Restoration Networks
论文作者
论文摘要
对图像的各种用户偏好最近引起了人们对控制图像恢复任务的图像效应的极大兴趣。但是，现有方法需要通过每个输出的整个网络进行单独的推论，这会阻碍用户容易比较长期延迟引起的多个图像效应。为此，我们提出了一个基于神经体系结构搜索技术的新型框架，该框架可以通过修剪的两个阶段有效地生成多个图像效应：任务不合时宜的和特定于任务的修剪。具体而言，特定于任务的修剪学会了为每个任务自适应地删除无关的网络参数，而任务不合时宜的修剪学会通过跨不同任务共享网络的早期层来寻找有效的体系结构。由于共享层允许重复使用功能，因此仅需要对任务不合时宜的层进行单个推断来从输入图像中生成多个图像效应。与基线相比，使用所提出的任务无关和特定于任务的修剪方案可显着降低拖鞋和实际推理的潜伏期。在产生27个图像效应时，我们减少了95.7％的失败，并使4K分辨率图像的GPU潜伏期更快。
Diverse user preferences over images have recently led to a great amount of interest in controlling the imagery effects for image restoration tasks. However, existing methods require separate inference through the entire network per each output, which hinders users from readily comparing multiple imagery effects due to long latency. To this end, we propose a novel framework based on a neural architecture search technique that enables efficient generation of multiple imagery effects via two stages of pruning: task-agnostic and task-specific pruning. Specifically, task-specific pruning learns to adaptively remove the irrelevant network parameters for each task, while task-agnostic pruning learns to find an efficient architecture by sharing the early layers of the network across different tasks. Since the shared layers allow for feature reuse, only a single inference of the task-agnostic layers is needed to generate multiple imagery effects from the input image. Using the proposed task-agnostic and task-specific pruning schemes together significantly reduces the FLOPs and the actual latency of inference compared to the baseline. We reduce 95.7% of the FLOPs when generating 27 imagery effects, and make the GPU latency 73.0% faster on 4K-resolution images.
