(PDF) Interventional few | 您所在的位置:网站首页 › interventional few shot › (PDF) Interventional few |
TL;DR: In this paper, the authors uncover an ever-overlooked deficiency in the prevailing few-shot learning (FSL) methods: the pre-trained knowledge is indeed a confounder that limits the performance. Abstract: We uncover an ever-overlooked deficiency in the prevailing Few-Shot Learning (FSL) methods: the pre-trained knowledge is indeed a confounder that limits the performance. This finding is rooted from our causal assumption: a Structural Causal Model (SCM) for the causalities among the pre-trained knowledge, sample features, and labels. Thanks to it, we propose a novel FSL paradigm: Interventional Few-Shot Learning (IFSL). Specifically, we develop three effective IFSL algorithmic implementations based on the backdoor adjustment, which is essentially a causal intervention towards the SCM of many-shot learning: the upper-bound of FSL in a causal view. It is worth noting that the contribution of IFSL is orthogonal to existing fine-tuning and meta-learning based FSL methods, hence IFSL can improve all of them, achieving a new 1-/5-shot state-of-the-art on \textit{mini}ImageNet, \textit{tiered}ImageNet, and cross-domain CUB. Code is released at this https URL. |
CopyRight 2018-2019 实验室设备网 版权所有 |