913 citations · 3.2k across the 60 of their papers we have counts for
12 papers · 1 filter
Prismer: A Vision-Language Model with Multi-Task Experts
Shikun Liu, Linxi Fan, Edward Johns +3
Recent vision-language models have shown impressive multi-modal generation capabilities. However, typically they require training huge models on massive datasets. As a more scalabl…
Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions
Jiachen Sun, Qingzhao Zhang, Bhavya Kailkhura +3
Deep neural networks on 3D point cloud data have been widely used in the real world, especially in safety-critical applications. However, their robustness against corruptions is le…
SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies
Linxi Fan, Guanzhi Wang, De-An Huang +4
Generalization has been a long-standing challenge for reinforcement learning (RL). Visual RL, in particular, can be easily distracted by irrelevant factors in high-dimensional obse…
Taxonomy of Machine Learning Safety: A Survey and Primer
Sina Mohseni, Haotao Wang, Zhiding Yu +3
The open-world deployment of Machine Learning (ML) algorithms in safety-critical applications such as autonomous vehicles needs to address a variety of ML vulnerabilities such as i…
Learning Calibrated Uncertainties for Domain Shift: A Distributionally Robust Learning Approach
Haoxuan Wang, Zhiding Yu, Yisong Yue +3
We propose a framework for learning calibrated uncertainties under domain shifts, where the source (training) distribution differs from the target (test) distribution. We detect su…
Automated Synthetic-to-Real Generalization
Wuyang Chen, Zhiding Yu, Zhangyang Wang +1
Models trained on synthetic images often face degraded generalization to real data. As a convention, these models are often initialized with ImageNet pre-trained representation. Ye…
Unsupervised Controllable Generation with Self-Training
Grigorios G Chrysos, Jean Kossaifi, Zhiding Yu +1
Recent generative adversarial networks (GANs) are able to generate impressive photo-realistic images. However, controllable generation with GANs remains a challenging research prob…
Neural Networks with Recurrent Generative Feedback
Yujia Huang, James Gornet, Sihui Dai +4
Neural networks are vulnerable to input perturbations such as additive noise and adversarial attacks. In contrast, human perception is much more robust to such perturbations. The B…
Angular Visual Hardness
Beidi Chen, Weiyang Liu, Zhiding Yu +4
Recent convolutional neural networks (CNNs) have led to impressive performance but often suffer from poor calibration. They tend to be overconfident, with the model confidence not…
Learning towards Minimum Hyperspherical Energy
Weiyang Liu, Rongmei Lin, Zhen Liu +4
Neural networks are a powerful class of nonlinear functions that can be trained end-to-end on various applications. While the over-parametrization nature in many neural networks re…
Robust Elastic Net Regression
Weiyang Liu, Rongmei Lin, Meng Yang
We propose a robust elastic net (REN) model for high-dimensional sparse regression and give its performance guarantees (both the statistical error bound and the optimization bound)…
Multi-Task Regularization with Covariance Dictionary for Linear Classifiers
Fanyi Xiao, Ruikun Luo, Zhiding Yu
In this paper we propose a multi-task linear classifier learning problem called D-SVM (Dictionary SVM). D-SVM uses a dictionary of parameter covariance shared by all tasks to do mu…