Search Results for author: Zhao Chen

Found 19 papers, 6 papers with code

近十年来澳门的词汇增长(Macau’s Vocabulary Growth in the Recent Ten Year)

no code implementations CCL 2021 Shan Wang, Zhao Chen, Haodi Zhang

“词汇增长模型可以通过拟合词种(types)与词例(tokens)之间的数量关系, 反映某一领域词汇的历时演化。澳门作为多语言多文化融合之地, 词汇的使用情况能够反映社会的关注焦点, 但目前尚无对澳门历时词汇演变的研究。本文首次构建澳门汉语历时语料库, 利用三大词汇增长模型拟合语料库的词汇变化, 并选取效果最好的 Heaps 模型进一步分析词汇演变与报刊内容的关系, 结果反映出澳门词汇的变化趋势与热点新闻、澳门施政方针和民生密切相关。本研究还采用去除文本时序信息后的乱序文本, 验证了方法的有效性。本文是首项基于大规模历时语料库考察澳门词汇演变的研究, 对深入了解澳门语言生活的发展具有重要意义。”

SHIFT3D: Synthesizing Hard Inputs For Tricking 3D Detectors

no code implementations ICCV 2023 Hongge Chen, Zhao Chen, Gregory P. Meyer, Dennis Park, Carl Vondrick, Ashish Shrivastava, Yuning Chai

We present SHIFT3D, a differentiable pipeline for generating 3D shapes that are structurally plausible yet challenging to 3D object detectors.

Autonomous Driving

Structural Inference of Networked Dynamical Systems with Universal Differential Equations

no code implementations11 Jul 2022 James Koch, Zhao Chen, Aaron Tuor, Jan Drgona, Draguna Vrabie

Networked dynamical systems are common throughout science in engineering; e. g., biological networks, reaction networks, power systems, and the like.

GradTail: Learning Long-Tailed Data Using Gradient-based Sample Weighting

no code implementations16 Jan 2022 Zhao Chen, Vincent Casser, Henrik Kretzschmar, Dragomir Anguelov

We propose GradTail, an algorithm that uses gradients to improve model performance on the fly in the face of long-tailed training data distributions.


Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout

1 code implementation NeurIPS 2020 Zhao Chen, Jiquan Ngiam, Yanping Huang, Thang Luong, Henrik Kretzschmar, Yuning Chai, Dragomir Anguelov

The vast majority of deep models use multiple gradient signals, typically corresponding to a sum of multiple loss terms, to update a shared set of trainable weights.

Transfer Learning

Sparse representation for damage identification of structural systems

no code implementations6 Jun 2020 Zhao Chen, Hao Sun

Specifically, an $\ell_2$ Bayesian learning method is firstly developed for updating the intact model and uncertainty quantification so as to set forward a baseline for damage detection.

Bayesian Optimization

Taskology: Utilizing Task Relations at Scale

no code implementations CVPR 2021 Yao Lu, Sören Pirk, Jan Dlabal, Anthony Brohan, Ankita Pasad, Zhao Chen, Vincent Casser, Anelia Angelova, Ariel Gordon

Many computer vision tasks address the problem of scene understanding and are naturally interrelated e. g. object classification, detection, scene segmentation, depth estimation, etc.

Depth Estimation Motion Estimation +3

Physics-informed learning of governing equations from scarce data

1 code implementation5 May 2020 Zhao Chen, Yang Liu, Hao Sun

Harnessing data to discover the underlying governing laws or equations that describe the behavior of complex physical systems can significantly advance our modeling, simulation and understanding of such systems in various science and engineering disciplines.

Model Discovery Representation Learning

The Weak Lensing Peak Statistics in the Mocks by the inverse-Gaussianization Method

1 code implementation29 Jan 2020 Zhao Chen, Yu Yu, Xiangkun Liu, Zuhui Fan

We apply the inverse-Gaussianization method proposed in \citealt{arXiv:1607. 05007} to fast produce weak lensing convergence maps and investigate the peak statistics, including the peak height counts and peak steepness counts, in these mocks.

Cosmology and Nongalactic Astrophysics

DeepPerimeter: Indoor Boundary Estimation from Posed Monocular Sequences

no code implementations25 Apr 2019 Ameya Phalak, Zhao Chen, Darvin Yi, Khushi Gupta, Vijay Badrinarayanan, Andrew Rabinovich

We present DeepPerimeter, a deep learning based pipeline for inferring a full indoor perimeter (i. e. exterior boundary map) from a sequence of posed RGB images.

Clustering Depth Estimation

Decentralized Computation Offloading for Multi-User Mobile Edge Computing: A Deep Reinforcement Learning Approach

2 code implementations16 Dec 2018 Zhao Chen, Xiaodong Wang

Numerical results are illustrated to demonstrate that efficient policies can be learned at each user, and performance of the proposed DDPG based decentralized strategy outperforms the conventional deep Q-network (DQN) based discrete power control strategy and some other greedy strategies with reduced computation cost.

Edge-computing Reinforcement Learning (RL)

Gradient Adversarial Training of Neural Networks

no code implementations21 Jun 2018 Ayan Sinha, Zhao Chen, Vijay Badrinarayanan, Andrew Rabinovich

We demonstrate gradient adversarial training for three different scenarios: (1) as a defense to adversarial examples we classify gradient tensors and tune them to be agnostic to the class of their corresponding example, (2) for knowledge distillation, we do binary classification of gradient tensors derived from the student or teacher network and tune the student gradient tensor to mimic the teacher's gradient tensor; and (3) for multi-task learning we classify the gradient tensors derived from different task loss functions and tune them to be statistically indistinguishable.

BIG-bench Machine Learning Binary Classification +2

Estimating Depth from RGB and Sparse Sensing

2 code implementations ECCV 2018 Zhao Chen, Vijay Badrinarayanan, Gilad Drozdov, Andrew Rabinovich

We present a deep model that can accurately produce dense depth maps given an RGB image with known depth at a very sparse set of pixels.

Monocular Depth Estimation

GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks

4 code implementations ICML 2018 Zhao Chen, Vijay Badrinarayanan, Chen-Yu Lee, Andrew Rabinovich

Deep multitask networks, in which one neural network produces multiple predictive outputs, can offer better speed and performance than their single-task counterparts but are challenging to train properly.

The Game Imitation: Deep Supervised Convolutional Networks for Quick Video Game AI

no code implementations18 Feb 2017 Zhao Chen, Darvin Yi

We present a vision-only model for gaming AI which uses a late integration deep convolutional network architecture trained in a purely supervised imitation learning context.

Imitation Learning Q-Learning

3-D Convolutional Neural Networks for Glioblastoma Segmentation

no code implementations14 Nov 2016 Darvin Yi, Mu Zhou, Zhao Chen, Olivier Gevaert

In this paper, we propose a framework of 3-D fully CNN models for Glioblastoma segmentation from multi-modality MRI data.

Cannot find the paper you are looking for? You can Submit a new open access paper.