14 citations · 51 across the 12 of their papers we have counts for
12 papers
Bayesian Cross-Modal Alignment Learning for Few-Shot Out-of-Distribution Generalization
Lin Zhu, Xinbing Wang, Chenghu Zhou +1
Recent advances in large pre-trained models showed promising results in few-shot learning. However, their generalization ability on two-dimensional Out-of-Distribution (OoD) data,…
BayesFT: Bayesian Optimization for Fault Tolerant Neural Network Architecture
Nanyang Ye, Jingbiao Mei, Zhicheng Fang +4
To deploy deep learning algorithms on resource-limited scenarios, an emerging device-resistive random access memory (ReRAM) has been regarded as promising via analog computing. How…
NAS-OoD: Neural Architecture Search for Out-of-Distribution Generalization
Haoyue Bai, Fengwei Zhou, Lanqing Hong +3
Recent advances on Out-of-Distribution (OoD) generalization reveal the robustness of deep learning models against distribution shifts. However, existing works focus on OoD algorith…
DeepIC: Coding for Interference Channels via Deep Learning
Karl Chahine, Nanyang Ye, Hyeji Kim
The two-user interference channel is a model for multi one-to-one communications, where two transmitters wish to communicate with their corresponding receivers via a shared wireles…
OoD-Bench: Quantifying and Understanding Two Dimensions of Out-of-Distribution Generalization
Nanyang Ye, Kaican Li, Haoyue Bai +5
Deep learning has achieved tremendous success with independent and identically distributed (i.i.d.) data. However, the performance of neural networks often degenerates drastically…
VeniBot: Towards Autonomous Venipuncture with Automatic Puncture Area and Angle Regression from NIR Images
Xu Cao, Zijie Chen, Bolin Lai +8
Venipucture is a common step in clinical scenarios, and is with highly practical value to be automated with robotics. Nowadays, only a few on-shelf robotic systems are developed, h…
VeniBot: Towards Autonomous Venipuncture with Semi-supervised Vein Segmentation from Ultrasound Images
Yu Chen, Yuxuan Wang, Bolin Lai +7
In the modern medical care, venipuncture is an indispensable procedure for both diagnosis and treatment. In this paper, unlike existing solutions that fully or partially rely on pr…
DecAug: Out-of-Distribution Generalization via Decomposed Feature Representation and Semantic Augmentation
Haoyue Bai, Rui Sun, Lanqing Hong +5
While deep learning demonstrates its strong ability to handle independent and identically distributed (IID) data, it often suffers from out-of-distribution (OoD) generalization, wh…
Batch Group Normalization
Xiao-Yun Zhou, Jiacheng Sun, Nanyang Ye +6
Deep Convolutional Neural Networks (DCNNs) are hard and time-consuming to train. Normalization is one of the effective solutions. Among previous normalization methods, Batch Normal…
Amata: An Annealing Mechanism for Adversarial Training Acceleration
Nanyang Ye, Qianxiao Li, Xiao-Yun Zhou +1
Despite the empirical success in various domains, it has been revealed that deep neural networks are vulnerable to maliciously perturbed input data that much degrade their performa…
Achieving Adversarial Robustness via Sparsity
Shufan Wang, Ningyi Liao, Liyao Xiang +2
Network pruning has been known to produce compact models without much accuracy degradation. However, how the pruning process affects a network's robustness and the working mechanis…
Langevin Dynamics with Continuous Tempering for Training Deep Neural Networks
Nanyang Ye, Zhanxing Zhu, Rafal K. Mantiuk
Minimizing non-convex and high-dimensional objective functions is challenging, especially when training modern deep neural networks. In this paper, a novel approach is proposed whi…