Robust Learning Through Cross-Task Consistency
CVPR(2020)
摘要
Visual perception entails solving a wide set of tasks (e.g., object detection, depth estimation, etc). The predictions made for different tasks out of one image are not independent, and therefore, are expected to be \u0027consistent\u0027. We propose a flexible and fully computational framework for learning while enforcing Cross-Task Consistency (X-TAC). The proposed formulation is based on \u0027inference path invariance\u0027 over an arbitrary graph of prediction domains. We observe that learning with cross-task consistency leads to more accurate predictions, better generalization to out-of-distribution samples, and improved sample efficiency. This framework also leads to a powerful unsupervised quantity, called \u0027Consistency Energy, based on measuring the intrinsic consistency of the system. Consistency Energy well correlates with the supervised error (r=0.67), thus it can be employed as an unsupervised robustness metric as well as for detection of out-of-distribution inputs (AUC=0.99). The evaluations were performed on multiple datasets, including Taskonomy, Replica, CocoDoom, and ApolloScape.
更多查看译文
关键词
learning,cross-task
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络