Taskonomy: Disentangling Task Transfer Learning

Do visual tasks have relationships, or are they unrelated? For instance, could having surface normals simplify estimating the depth of an image? Intuition answers these questions positively, implying existence of a certain structure among visual tasks. Knowing this structure has notable values; it provides a principled way for identifying relationships across tasks, for instance, in order to reuse supervision among tasks with redundancies or solve many tasks in one system without piling up the complexity. We propose a fully computational approach for modeling the transfer learning structure of the space of visual tasks. This is done via finding transfer learning dependencies across tasks in a dictionary of twenty-six 2D, 2. 5D, 3D, and semantic tasks. The product is a computational taxonomic map among tasks for transfer learning, and we exploit it to reduce the demand for labeled data. For example, we show that the total number of labeled datapoints needed for solving a set of 10 tasks can be reduced by roughly 2/3 (compared to training independently) while keeping the performance nearly the same. We provide a set of tools for computing and visualizing this taxonomical structure at http: //taskonomy. vision.

Authors

• Amir Zamir
• Alexander Sax
• William Shen
• Leonidas Guibas
• Jitendra Malik
• Silvio Savarese Salesforce AI Research

Keywords

• Computer Vision: 2D and 3D Computer Vision
• Computer Vision: Computer Vision
• Machine Learning: Deep Learning
• Machine Learning: Transfer, Adaptation, Multi-task Learning