no code implementations • ICLR 2022 • Jiechao Guan, Zhiwu Lu
Supposing the $n$ training tasks and the new task are sampled from the same environment, traditional meta learning theory derives an error bound on the expected loss over the new task in terms of the empirical training loss, uniformly over the set of all hypothesis spaces.
no code implementations • 29 Sep 2021 • Jiechao Guan, Zhiwu Lu, Yong liu
In particular, we identify that when the number of training task is large, utilizing a prior generated from an informative hyperposterior can achieve the same order of PAC-Bayes-kl bound as that obtained through setting a localized distribution-dependent prior for a novel task.
no code implementations • 2 Dec 2020 • Jiechao Guan, Zhiwu Lu, Tao Xiang, Timothy Hospedales
By transferring knowledge learned from seen/previous tasks, meta learning aims to generalize well to unseen/future tasks.
1 code implementation • 19 Mar 2020 • An Zhao, Mingyu Ding, Zhiwu Lu, Tao Xiang, Yulei Niu, Jiechao Guan, Ji-Rong Wen, Ping Luo
Existing few-shot learning (FSL) methods make the implicit assumption that the few target class samples are from the same domain as the source class samples.
no code implementations • 6 Feb 2020 • Jiechao Guan, Zhiwu Lu, Tao Xiang, Ji-Rong Wen
Specifically, armed with a set transformer based attention module, we construct each episode with two sub-episodes without class overlap on the seen classes to simulate the domain shift between the seen and unseen classes.
no code implementations • 11 Dec 2018 • Nanyi Fei, Jiechao Guan, Zhiwu Lu, Tao Xiang, Ji-Rong Wen
The standard approach to ZSL requires a set of training images annotated with seen class labels and a semantic descriptor for seen/unseen classes (attribute vector is the most widely used).
no code implementations • 19 Oct 2018 • Zhiwu Lu, Jiechao Guan, Aoxue Li, Tao Xiang, An Zhao, Ji-Rong Wen
Specifically, we assume that each synthesised data point can belong to any unseen class; and the most likely two class candidates are exploited to learn a robust projection function in a competitive fashion.
no code implementations • 19 Oct 2018 • Aoxue Li, Zhiwu Lu, Jiechao Guan, Tao Xiang, Li-Wei Wang, Ji-Rong Wen
Inspired by the fact that an unseen class is not exactly `unseen' if it belongs to the same superclass as a seen class, we propose a novel inductive ZSL model that leverages superclasses as the bridge between seen and unseen classes to narrow the domain gap.
no code implementations • NeurIPS 2018 • An Zhao, Mingyu Ding, Jiechao Guan, Zhiwu Lu, Tao Xiang, Ji-Rong Wen
This is made possible by learning a projection between a feature space and a semantic space (e. g. attribute space).