论文标题
通用表示：统一查看多个任务和领域学习
Universal Representations: A Unified Look at Multiple Task and Domain Learning
论文作者
论文摘要
我们提出了一个统一的查看，即通过通用表示，一个深层的神经网络共同学习多个视觉任务和视觉域。同时学习多个问题涉及最大程度地减少具有不同幅度和特征的多个损失函数的加权总和，从而导致一个损失的不平衡状态，与学习每个问题的单独模型相比，一个损失的不平衡状态主导了优化和差的结果。为此，我们建议通过小容量适配器将多个任务/特定于域网络的知识与单个深层神经网络进行提炼知识。我们严格地表明，通用表示在学习NYU-V2和CityScapes中多个密集的预测问题方面实现了最新的表现，来自视觉十项全能数据集中不同领域的多个图像分类问题以及元数据中的跨域中几乎没有研究。最后，我们还通过消融和定性研究进行多次分析。
We propose a unified look at jointly learning multiple vision tasks and visual domains through universal representations, a single deep neural network. Learning multiple problems simultaneously involves minimizing a weighted sum of multiple loss functions with different magnitudes and characteristics and thus results in unbalanced state of one loss dominating the optimization and poor results compared to learning a separate model for each problem. To this end, we propose distilling knowledge of multiple task/domain-specific networks into a single deep neural network after aligning its representations with the task/domain-specific ones through small capacity adapters. We rigorously show that universal representations achieve state-of-the-art performances in learning of multiple dense prediction problems in NYU-v2 and Cityscapes, multiple image classification problems from diverse domains in Visual Decathlon Dataset and cross-domain few-shot learning in MetaDataset. Finally we also conduct multiple analysis through ablation and qualitative studies.
