AI 研習社論文推薦版塊已經正式上線，歡迎大家前往社區論文板塊查閱喔~

www.gair.link/page/paper

Taskonomy: Disentangling Task Transfer Learning

Zamir Amir /Sax Alexander /Shen William /Guibas Leonidas /Malik Jitendra /Savarese Silvio

推薦原因

這是一篇難得一見的「大視角」論文。絕大多數計算機視覺論文都研究的是某個具體問題的具體方法，這當然不算錯，但我們總還是需要一些別的視角來對整個計算機視覺領域加以理解。這篇論文就研究了不同計算機視覺任務之間的聯繫，而這些聯繫就可以對我們如何選擇數據、如何選擇方法、如何在不同的任務之間遷移方法提供高屋建瓴的指導。不出意外地，這篇論文獲得了CVPR2018的最佳論文獎。論文詳細解讀文章請點擊：CVPR18最佳論文演講：研究任務之間的聯繫才是做遷移學習的正確姿勢

來自AI研習社用戶@楊 曉凡的推薦

摘要

Do visual tasks have a relationship, 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 structure among visual tasks. Knowing this structure has notable values; it is the concept underlying transfer learning and provides a principled way for identifying redundancies across tasks, e.g., to seamlessly reuse supervision among related tasks or solve many tasks in one system without piling up the complexity. We proposes a fully computational approach for modeling the structure of space of visual tasks. This is done via finding (first and higher-order) transfer learning dependencies across a dictionary of twenty six 2D, 2.5D, 3D, and semantic tasks in a latent space. The product is a computational taxonomic map for task transfer learning. We study the consequences of this structure, e.g. nontrivial emerged relationships, and exploit them 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 probing this taxonomical structure including a solver that users can employ to devise efficient supervision policies for their use cases.

喜歡這篇文章嗎？立刻分享出去讓更多人知道吧！