Search Results for author: Xingxuan Zhang

Found 10 papers, 3 papers with code

NICO++: Towards Better Benchmarking for Domain Generalization

1 code implementation17 Apr 2022 Xingxuan Zhang, Yue He, Renzhe Xu, Han Yu, Zheyan Shen, Peng Cui

Most current evaluation methods for domain generalization (DG) adopt the leave-one-out strategy as a compromise on the limited number of domains.

Domain Generalization Generalization Bounds +1

Towards Domain Generalization in Object Detection

no code implementations27 Mar 2022 Xingxuan Zhang, Zekai Xu, Renzhe Xu, Jiashuo Liu, Peng Cui, Weitao Wan, Chong Sun, Chen Li

Despite the striking performance achieved by modern detectors when training and test data are sampled from the same or similar distribution, the generalization ability of detectors under unknown distribution shifts remains hardly studied.

Domain Generalization Object Detection

Regulatory Instruments for Fair Personalized Pricing

1 code implementation9 Feb 2022 Renzhe Xu, Xingxuan Zhang, Peng Cui, Bo Li, Zheyan Shen, Jiazheng Xu

Personalized pricing is a business strategy to charge different prices to individual consumers based on their characteristics and behaviors.

Why Stable Learning Works? A Theory of Covariate Shift Generalization

no code implementations3 Nov 2021 Renzhe Xu, Peng Cui, Zheyan Shen, Xingxuan Zhang, Tong Zhang

We first specify a set of variables, named minimal stable variable set, that is minimal and optimal to deal with covariate shift generalization for common loss functions, including the mean squared loss and binary cross entropy loss.

Towards Out-Of-Distribution Generalization: A Survey

no code implementations31 Aug 2021 Zheyan Shen, Jiashuo Liu, Yue He, Xingxuan Zhang, Renzhe Xu, Han Yu, Peng Cui

Classic machine learning methods are built on the $i. i. d.$ assumption that training and testing data are independent and identically distributed.

Out-of-Distribution Generalization Representation Learning

Towards Unsupervised Domain Generalization

no code implementations13 Jul 2021 Xingxuan Zhang, Linjun Zhou, Renzhe Xu, Peng Cui, Zheyan Shen, Haoxin Liu

Domain generalization (DG) aims to help models trained on a set of source domains generalize better on unseen target domains.

Domain Generalization Representation Learning

Deep Stable Learning for Out-Of-Distribution Generalization

1 code implementation CVPR 2021 Xingxuan Zhang, Peng Cui, Renzhe Xu, Linjun Zhou, Yue He, Zheyan Shen

Approaches based on deep neural networks have achieved striking performance when testing data and training data share similar distribution, but can significantly fail otherwise.

Domain Generalization Out-of-Distribution Generalization

Sample Balancing for Improving Generalization under Distribution Shifts

no code implementations1 Jan 2021 Xingxuan Zhang, Peng Cui, Renzhe Xu, Yue He, Linjun Zhou, Zheyan Shen

We propose to address this problem by removing the dependencies between features via reweighting training samples, which results in a more balanced distribution and helps deep models get rid of spurious correlations and, in turn, concentrate more on the true connection between features and labels.

Domain Adaptation Object Recognition

Spatio-Temporal Fusion Based Convolutional Sequence Learning for Lip Reading

no code implementations ICCV 2019 Xingxuan Zhang, Feng Cheng, Shilin Wang

Current state-of-the-art approaches for lip reading are based on sequence-to-sequence architectures that are designed for natural machine translation and audio speech recognition.

Ranked #9 on Lipreading on LRS2 (using extra training data)

Lipreading Lip Reading +3

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