343 citations · 372 across the 4 of their papers we have counts for
7 papers
Patch-wise Attack for Fooling Deep Neural Network
Lianli Gao, Qilong Zhang, Jingkuan Song +2
By adding human-imperceptible noise to clean images, the resultant adversarial examples can fool other unknown models. Features of a pixel extracted by deep neural networks (DNNs)…
Improving Target-driven Visual Navigation with Attention on 3D Spatial Relationships
Yunlian Lv, Ning Xie, Yimin Shi +2
Embodied artificial intelligence (AI) tasks shift from tasks focusing on internet images to active settings involving embodied agents that perceive and act within 3D environments.…
Maximum Density Divergence for Domain Adaptation
Li Jingjing, Chen Erpeng, Ding Zhengming +3
Unsupervised domain adaptation addresses the problem of transferring knowledge from a well-labeled source domain to an unlabeled target domain where the two domains have distinctiv…
MetaMixUp: Learning Adaptive Interpolation Policy of MixUp with Meta-Learning
Zhijun Mai, Guosheng Hu, Dexiong Chen +2
MixUp is an effective data augmentation method to regularize deep neural networks via random linear interpolations between pairs of samples and their labels. It plays an important…
Temporal Reasoning Graph for Activity Recognition
Jingran Zhang, Fumin Shen, Xing Xu +1
Despite great success has been achieved in activity analysis, it still has many challenges. Most existing work in activity recognition pay more attention to design efficient archit…
Locality Preserving Joint Transfer for Domain Adaptation
Li Jingjing, Jing Mengmeng, Lu Ke +2
Domain adaptation aims to leverage knowledge from a well-labeled source domain to a poorly-labeled target domain. A majority of existing works transfer the knowledge at either feat…