Timezone: »

Interventional Few-Shot Learning
Zhongqi Yue · Hanwang Zhang · Qianru Sun · Xian-Sheng Hua

Mon Dec 07 09:00 PM -- 11:00 PM (PST) @ Poster Session 0 #14

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 miniImageNet, tieredImageNet, and cross-domain CUB. Code is released at https://github.com/yue-zhongqi/ifsl.

Author Information

Zhongqi Yue (Nanyang Technological University)
Hanwang Zhang (NTU)
Qianru Sun (Singapore Management University)
Xian-Sheng Hua (Damo Academy, Alibaba Group)

More from the Same Authors