no code implementations • 25 May 2023 • Zheyan Shen, Han Yu, Peng Cui, Jiashuo Liu, Xingxuan Zhang, Linjun Zhou, Furui Liu
Moreover, we propose a Meta Adaptive Task Sampling (MATS) procedure to differentiate base tasks according to their semantic and domain-shift similarity to the novel task.
no code implementations • 22 Feb 2022 • Zhuolin Wu, Li Wang, Fangsheng Huang, Linjun Zhou, Yu Song, Chengpeng Ye, Pengyu Nie, Hao Ren, Jinghua Hao, Renqing He, Zhizhao Sun
The semi-black-box acceptance probability model is employed to forecast the relationship between the bonus allocated to order and its acceptance probability, the Lagrangian dual-based dynamic programming algorithm aims to calculate the empirical Lagrangian multiplier for each allocation stage offline based on the historical data set, and the online allocation algorithm uses the results attained in the offline part to calculate a proper delivery bonus for each order.
no code implementations • CVPR 2022 • 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.
no code implementations • 30 Jun 2021 • Jiashuo Liu, Zheyan Shen, Peng Cui, Linjun Zhou, Kun Kuang, Bo Li
In this paper, we propose a novel Stable Adversarial Learning (SAL) algorithm that leverages heterogeneous data sources to construct a more practical uncertainty set and conduct differentiated robustness optimization, where covariates are differentiated according to the stability of their correlations with the target.
2 code implementations • 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.
Ranked #28 on Domain Generalization on VLCS
no code implementations • 1 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.
no code implementations • CVPR 2022 • Linjun Zhou, Peng Cui, Yinan Jiang, Shiqiang Yang
In this paper, we propose a novel setting of transferable black-box attack: attackers may use external information from a pre-trained model with available network parameters, however, different from previous studies, no additional training data is permitted to further change or tune the pre-trained model.
1 code implementation • 18 Jun 2020 • Renzhe Xu, Peng Cui, Kun Kuang, Bo Li, Linjun Zhou, Zheyan Shen, Wei Cui
In practice, there frequently exist a certain set of variables we term as fair variables, which are pre-decision covariates such as users' choices.
no code implementations • 8 Jun 2020 • Jiashuo Liu, Zheyan Shen, Peng Cui, Linjun Zhou, Kun Kuang, Bo Li, Yishi Lin
Machine learning algorithms with empirical risk minimization are vulnerable under distributional shifts due to the greedy adoption of all the correlations found in training data.
no code implementations • CVPR 2020 • Linjun Zhou, Peng Cui, Xu Jia, Shiqiang Yang, Qi Tian
Few-shot learning has attracted intensive research attention in recent years.
no code implementations • CVPR 2019 • Linjun Zhou, Peng Cui, Shiqiang Yang, Wenwu Zhu, Qi Tian
We then propose an out-of-sample embedding method to learn the embedding of a new class represented by a few samples through its visual analogy with base classes and derive the classification parameters for the new class.