Search Results for author: Jiayi Shen

Found 20 papers, 8 papers with code

Eliminating the Invariance on the Loss Landscape of Linear Autoencoders

no code implementations ICML 2020 Reza Oftadeh, Jiayi Shen, Zhangyang Wang, Dylan Shell

For this new loss, we characterize the full structure of the loss landscape in the following sense: we establish analytical expression for the set of all critical points, show that it is a subset of critical points of MSE, and that all local minima are still global.


GO4Align: Group Optimization for Multi-Task Alignment

1 code implementation9 Apr 2024 Jiayi Shen, Cheems Wang, Zehao Xiao, Nanne van Noord, Marcel Worring

This paper proposes \textit{GO4Align}, a multi-task optimization approach that tackles task imbalance by explicitly aligning the optimization across tasks.

Any-Shift Prompting for Generalization over Distributions

no code implementations15 Feb 2024 Zehao Xiao, Jiayi Shen, Mohammad Mahdi Derakhshani, Shengcai Liao, Cees G. M. Snoek

To effectively encode the distribution information and their relationships, we further introduce a transformer inference network with a pseudo-shift training mechanism.

Language Modelling

Learning Variational Neighbor Labels for Test-Time Domain Generalization

no code implementations8 Jul 2023 Sameer Ambekar, Zehao Xiao, Jiayi Shen, XianTong Zhen, Cees G. M. Snoek

We formulate the generalization at test time as a variational inference problem by modeling pseudo labels as distributions to consider the uncertainty during generalization and alleviate the misleading signal of inaccurate pseudo labels.

Domain Generalization Variational Inference

EMO: Episodic Memory Optimization for Few-Shot Meta-Learning

no code implementations8 Jun 2023 Yingjun Du, Jiayi Shen, XianTong Zhen, Cees G. M. Snoek

By learning to retain and recall the learning process of past training tasks, EMO nudges parameter updates in the right direction, even when the gradients provided by a limited number of examples are uninformative.

Few-Shot Learning

E^2VTS: Energy-Efficient Video Text Spotting from Unmanned Aerial Vehicles

1 code implementation5 Jun 2022 Zhenyu Hu, Zhenyu Wu, Pengcheng Pi, Yunhe Xue, Jiayi Shen, Jianchao Tan, Xiangru Lian, Zhangyang Wang, Ji Liu

Unmanned Aerial Vehicles (UAVs) based video text spotting has been extensively used in civil and military domains.

Text Spotting

NFormer: Robust Person Re-identification with Neighbor Transformer

1 code implementation CVPR 2022 Haochen Wang, Jiayi Shen, Yongtuo Liu, Yan Gao, Efstratios Gavves

To tackle this issue, we propose a Neighbor Transformer Network, or NFormer, which explicitly models interactions across all input images, thus suppressing outlier features and leading to more robust representations overall.

Person Re-Identification Representation Learning

Multi-Task Neural Processes

no code implementations10 Nov 2021 Jiayi Shen, XianTong Zhen, Marcel Worring, Ling Shao

Our multi-task neural processes methodologically expand the scope of vanilla neural processes and provide a new way of exploring task relatedness in function spaces for multi-task learning.

Bayesian Inference Brain Image Segmentation +4

Variational Multi-Task Learning with Gumbel-Softmax Priors

1 code implementation NeurIPS 2021 Jiayi Shen, XianTong Zhen, Marcel Worring, Ling Shao

Multi-task learning aims to explore task relatedness to improve individual tasks, which is of particular significance in the challenging scenario that only limited data is available for each task.

Bayesian Inference Multi-Task Learning

A Bit More Bayesian: Domain-Invariant Learning with Uncertainty

1 code implementation9 May 2021 Zehao Xiao, Jiayi Shen, XianTong Zhen, Ling Shao, Cees G. M. Snoek

Domain generalization is challenging due to the domain shift and the uncertainty caused by the inaccessibility of target domain data.

Bayesian Inference Domain Generalization

Variational Multi-Task Learning

no code implementations1 Jan 2021 Jiayi Shen, XianTong Zhen, Marcel Worring, Ling Shao

Multi-task learning aims to improve the overall performance of a set of tasks by leveraging their relatedness.

Bayesian Inference Inductive Bias +1

Variational Invariant Learning for Bayesian Domain Generalization

no code implementations1 Jan 2021 Zehao Xiao, Jiayi Shen, XianTong Zhen, Ling Shao, Cees G. M. Snoek

In the probabilistic modeling framework, we introduce a domain-invariant principle to explore invariance across domains in a unified way.

Domain Generalization

Learning A Minimax Optimizer: A Pilot Study

no code implementations ICLR 2021 Jiayi Shen, Xiaohan Chen, Howard Heaton, Tianlong Chen, Jialin Liu, Wotao Yin, Zhangyang Wang

We first present Twin L2O, the first dedicated minimax L2O framework consisting of two LSTMs for updating min and max variables, respectively.

Neural Networks for Principal Component Analysis: A New Loss Function Provably Yields Ordered Exact Eigenvectors

no code implementations25 Sep 2019 Reza Oftadeh, Jiayi Shen, Zhangyang Wang, Dylan Shell

In this paper, we propose a new loss function for performing principal component analysis (PCA) using linear autoencoders (LAEs).


Cannot find the paper you are looking for? You can Submit a new open access paper.