20 citations · 22 across the 5 of their papers we have counts for
5 papers
Confidence Matters: Inspecting Backdoors in Deep Neural Networks via Distribution Transfer
Tong Wang, Yuan Yao, Feng Xu +3
Backdoor attacks have been shown to be a serious security threat against deep learning models, and detecting whether a given model has been backdoored becomes a crucial task. Exist…
DenseGAP: Graph-Structured Dense Correspondence Learning with Anchor Points
Zhengfei Kuang, Jiaman Li, Mingming He +2
Establishing dense correspondence between two images is a fundamental computer vision problem, which is typically tackled by matching local feature descriptors. However, without gl…
Backdoor Attack through Frequency Domain
Tong Wang, Yuan Yao, Feng Xu +3
Backdoor attacks have been shown to be a serious threat against deep learning systems such as biometric authentication and autonomous driving. An effective backdoor attack could en…
Diverse Distributions of Self-Supervised Tasks for Meta-Learning in NLP
Trapit Bansal, Karthick Gunasekaran, Tong Wang +2
Meta-learning considers the problem of learning an efficient learning process that can leverage its past experience to accurately solve new tasks. However, the efficacy of meta-lea…
Task-adaptive Asymmetric Deep Cross-modal Hashing
Fengling Li, Tong Wang, Lei Zhu +2
Supervised cross-modal hashing aims to embed the semantic correlations of heterogeneous modality data into the binary hash codes with discriminative semantic labels. Because of its…