TransNAS-Bench-101: Improving transferability and Generalizability of Cross-Task Neural Architecture Search
TransNAS-Bench-101: Improving transferability and Generalizability of Cross-Task Neural Architecture Search
复制标题
DOI：
10.1109/cvpr46437.2021.00521
复制
发表时间：
2020-09
期刊：
影响因子：
--
通讯作者：
Yawen Duan;Xin Chen;Hang Xu;Zewei Chen;Li Xiaodan;Tong Zhang;Zhenguo Li
中科院分区：
文献类型：
--
作者：
Yawen Duan;Xin Chen;Hang Xu;Zewei Chen;Li Xiaodan;Tong Zhang;Zhenguo Li
神经架构搜索（NAS）的最新突破将该领域的研究范围扩展到更广泛的视觉任务和更多样化的搜索空间。虽然现有的NAS方法主要针对单个任务设计架构，但超越单任务搜索的算法正在寻求跨各种任务的更高效和通用的解决方案。他们中的许多人利用迁移学习，并寻求保留，重用和改进网络设计知识，以在未来的任务中实现更高的效率。然而，跨任务NAS的巨大计算成本和实验复杂性给这一方向的有价值的研究带来了障碍。现有的NAS基准测试都集中在一种类型的视觉任务上，即，分类.在这项工作中，我们提出了TransNAS-Bench-101，这是一个基准数据集，包含七个任务的网络性能，包括分类，回归，像素级预测和自我监督任务。这种多样性提供了在任务之间转移NAS方法的机会，并允许发展更复杂的转移方案。我们探索两种根本不同类型的搜索空间：细胞级搜索空间和宏观级搜索空间。通过对7个任务的7，352个骨干进行评估，提供了51，464个具有详细训练信息的训练模型。通过TransNAS-Bench-101，我们希望鼓励出现特殊的NAS算法，将跨任务搜索效率和通用性提高到一个新的水平。我们的数据集和代码将在Mindspore 1和VEGA 2上提供。
Recent breakthroughs of Neural Architecture Search (NAS) extend the field’s research scope towards a broader range of vision tasks and more diversified search spaces. While existing NAS methods mostly design architectures on a single task, algorithms that look beyond single-task search are surging to pursue a more efficient and universal solution across various tasks. Many of them leverage transfer learning and seek to preserve, reuse, and refine network design knowledge to achieve higher efficiency in future tasks. However, the enormous computational cost and experiment complexity of cross-task NAS are imposing barriers for valuable research in this direction. Existing NAS benchmarks all focus on one type of vision task, i.e., classification. In this work, we propose TransNAS-Bench-101, a benchmark dataset containing network performance across seven tasks, covering classification, regression, pixel-level prediction, and self-supervised tasks. This diversity provides opportunities to transfer NAS methods among tasks and allows for more complex transfer schemes to evolve. We explore two fundamentally different types of search space: cell-level search space and macro-level search space. With 7,352 backbones evaluated on seven tasks, 51,464 trained models with detailed training information are provided. With TransNAS-Bench-101, we hope to encourage the advent of exceptional NAS algorithms that raise cross-task search efficiency and generalizability to the next level. Our dataset and code will be available at Mindspore1 and VEGA2.