Keywords: few-shot learning, causal intervention, matching networks, maml, leo, mtl
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 FewShot 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 miniImageNet,
tieredImageNet, and cross-domain CUB. Code is released at https://github.
com/yue-zhongqi/ifsl.
Paper Url: https://openreview.net/forum?id=880g0xFnboZ&referrer=%5BML%20Reproducibility%20Challenge%202020%5D(%2Fgroup%3Fid%3DML_Reproducibility_Challenge%2F2020)
4 Replies
Loading