37 citations · 175 across the 13 of their papers we have counts for
13 papers
Moderately Distributional Exploration for Domain Generalization
Rui Dai, Yonggang Zhang, Zhen Fang +2
Domain generalization (DG) aims to tackle the distribution shift between training domains and unknown target domains. Generating new domains is one of the most effective approaches…
Is Out-of-Distribution Detection Learnable?
Zhen Fang, Yixuan Li, Jie Lu +3
Supervised learning aims to train a classifier under the assumption that training and test data are from the same distribution. To ease the above assumption, researchers have studi…
Multi-class Classification with Fuzzy-feature Observations: Theory and Algorithms
Guangzhi Ma, Jie Lu, Feng Liu +2
The theoretical analysis of multi-class classification has proved that the existing multi-class classification methods can train a classifier with high classification accuracy on t…
Federated Class-Incremental Learning
Jiahua Dong, Lixu Wang, Zhen Fang +4
Federated learning (FL) has attracted growing attention via data-private collaborative training on decentralized clients. However, most existing methods unrealistically assume obje…
Learning Bounds for Open-Set Learning
Zhen Fang, Jie Lu, Anjin Liu +2
Traditional supervised learning aims to train a classifier in the closed-set world, where training and test samples share the same label space. In this paper, we target a more chal…
NMS-Loss: Learning with Non-Maximum Suppression for Crowded Pedestrian Detection
Zekun Luo, Zheng Fang, Sixiao Zheng +2
Non-Maximum Suppression (NMS) is essential for object detection and affects the evaluation results by incorporating False Positives (FP) and False Negatives (FN), especially in cro…
How does the Combined Risk Affect the Performance of Unsupervised Domain Adaptation Approaches?
Li Zhong, Zhen Fang, Feng Liu +3
Unsupervised domain adaptation (UDA) aims to train a target classifier with labeled samples from the source domain and unlabeled samples from the target domain. Classical UDA learn…
Learning from a Complementary-label Source Domain: Theory and Algorithms
Yiyang Zhang, Feng Liu, Zhen Fang +3
In unsupervised domain adaptation (UDA), a classifier for the target domain is trained with massive true-label data from the source domain and unlabeled data from the target domain…
Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation
Yiyang Zhang, Feng Liu, Zhen Fang +3
In unsupervised domain adaptation (UDA), classifiers for the target domain are trained with massive true-label data from the source domain and unlabeled data from the target domain…
Bridging the Theoretical Bound and Deep Algorithms for Open Set Domain Adaptation
Li Zhong, Zhen Fang, Feng Liu +3
In the unsupervised open set domain adaptation (UOSDA), the target domain contains unknown classes that are not observed in the source domain. Researchers in this area aim to train…
Learning to Order Sub-questions for Complex Question Answering
Yunan Zhang, Xiang Cheng, Yufeng Zhang +5
Answering complex questions involving multiple entities and relations is a challenging task. Logically, the answer to a complex question should be derived by decomposing the comple…
Open Set Domain Adaptation: Theoretical Bound and Algorithm
Zhen Fang, Jie Lu, Feng Liu +2
The aim of unsupervised domain adaptation is to leverage the knowledge in a labeled (source) domain to improve a model's learning performance with an unlabeled (target) domain -- t…
DenseBody: Directly Regressing Dense 3D Human Pose and Shape From a Single Color Image
Pengfei Yao, Zheng Fang, Fan Wu +2
Recovering 3D human body shape and pose from 2D images is a challenging task due to high complexity and flexibility of human body, and relatively less 3D labeled data. Previous met…