551 citations · 2.3k across the 76 of their papers we have counts for
14 papers · 1 filter
Surrogate Gap Minimization Improves Sharpness-Aware Training
Juntang Zhuang, Boqing Gong, Liangzhe Yuan +6
The recently proposed Sharpness-Aware Minimization (SAM) improves generalization by minimizing a \textit{perturbed loss} defined as the maximum loss within a neighborhood in the pa…
Large-Scale Meta-Learning with Continual Trajectory Shifting
Jaewoong Shin, Hae Beom Lee, Boqing Gong +1
Meta-learning of shared initialization parameters has shown to be highly effective in solving few-shot learning tasks. However, extending the framework to many-shot scenarios, whic…
Ranking Neural Checkpoints
Yandong Li, Xuhui Jia, Ruoxin Sang +4
This paper is concerned with ranking many pre-trained deep neural networks (DNNs), called checkpoints, for the transfer learning to a downstream task. Thanks to the broad use of DN…
Smooth Adversarial Training
Cihang Xie, Mingxing Tan, Boqing Gong +2
It is commonly believed that networks cannot be both accurate and robust, that gaining robustness means losing accuracy. It is also generally believed that, unless making networks…
When Ensembling Smaller Models is More Efficient than Single Large Models
Dan Kondratyuk, Mingxing Tan, Matthew Brown +1
Ensembling is a simple and popular technique for boosting evaluation performance by training multiple models (e.g., with different initializations) and aggregating their prediction…
MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radius
Runtian Zhai, Chen Dan, Di He +5
Adversarial training is one of the most popular ways to learn robust models but is usually attack-dependent and time costly. In this paper, we propose the MACER algorithm, which le…
NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networks
Yandong Li, Lijun Li, Liqiang Wang +2
Powerful adversarial attack methods are vital for understanding how to construct robust deep neural networks (DNNs) and for thoroughly testing defense techniques. In this paper, we…
Synthesized Policies for Transfer and Adaptation across Tasks and Environments
Hexiang Hu, Liyu Chen, Boqing Gong +1
The ability to transfer in reinforcement learning is key towards building an agent of general artificial intelligence. In this paper, we consider the problem of learning to simulta…
Joint Modeling of Dense and Incomplete Trajectories for Citywide Traffic Volume Inference
Xianfeng Tang, Boqing Gong, Yanwei Yu +4
Real-time traffic volume inference is key to an intelligent city. It is a challenging task because accurate traffic volumes on the roads can only be measured at certain locations w…
Improving Sequential Determinantal Point Processes for Supervised Video Summarization
Aidean Sharghi, Ali Borji, Chengtao Li +2
It is now much easier than ever before to produce videos. While the ubiquitous video data is a great source for information discovery and extraction, the computational challenges a…
Defend Deep Neural Networks Against Adversarial Examples via Fixed and Dynamic Quantized Activation Functions
Adnan Siraj Rakin, Jinfeng Yi, Boqing Gong +1
Recent studies have shown that deep neural networks (DNNs) are vulnerable to adversarial attacks. To this end, many defense approaches that attempt to improve the robustness of DNN…
Blind Pre-Processing: A Robust Defense Method Against Adversarial Examples
Adnan Siraj Rakin, Zhezhi He, Boqing Gong +1
Deep learning algorithms and networks are vulnerable to perturbed inputs which is known as the adversarial attack. Many defense methodologies have been investigated to defend again…
Infinite-Label Learning with Semantic Output Codes
Yang Zhang, Rupam Acharyya, Ji Liu +1
We develop a new statistical machine learning paradigm, named infinite-label learning, to annotate a data point with more than one relevant labels from a candidate set, which pools…
Improved Dropout for Shallow and Deep Learning
Zhe Li, Boqing Gong, Tianbao Yang
Dropout has been witnessed with great success in training deep neural networks by independently zeroing out the outputs of neurons at random. It has also received a surge of intere…