Search Results for author: Qi Guo

Found 24 papers, 5 papers with code

Neural Program Synthesis with Query

no code implementations ICLR 2022 Di Huang, Rui Zhang, Xing Hu, Xishan Zhang, Pengwei Jin, Nan Li, Zidong Du, Qi Guo, Yunji Chen

In this work, we propose a query-based framework that trains a query neural network to generate informative input-output examples automatically and interactively from a large query space.

ScaleCert: Scalable Certified Defense against Adversarial Patches with Sparse Superficial Layers

no code implementations NeurIPS 2021 Husheng Han, Kaidi Xu, Xing Hu, Xiaobing Chen, Ling Liang, Zidong Du, Qi Guo, Yanzhi Wang, Yunji Chen

Our experimental results show that the certified accuracy is increased from 36. 3% (the state-of-the-art certified detection) to 60. 4% on the ImageNet dataset, largely pushing the certified defenses for practical use.

Hindsight Value Function for Variance Reduction in Stochastic Dynamic Environment

no code implementations26 Jul 2021 Jiaming Guo, Rui Zhang, Xishan Zhang, Shaohui Peng, Qi Yi, Zidong Du, Xing Hu, Qi Guo, Yunji Chen

In this paper, we propose to replace the state value function with a novel hindsight value function, which leverages the information from the future to reduce the variance of the gradient estimate for stochastic dynamic environments.

Policy Gradient Methods

Improving Dialogue Breakdown Detection with Semi-Supervised Learning

no code implementations30 Oct 2020 Nathan Ng, Marzyeh Ghassemi, Narendran Thangarajan, Jiacheng Pan, Qi Guo

In ablations on DBDC4 data from 2019, our semi-supervised learning methods improve the performance of a baseline BERT model by 2\% accuracy.

Data Augmentation

MOTS: Multiple Object Tracking for General Categories Based On Few-Shot Method

no code implementations19 May 2020 Xixi Xu, Chao Lu, Liang Zhu, xiangyang xue, Guanxian Chen, Qi Guo, Yining Lin, Zhijian Zhao

Most modern Multi-Object Tracking (MOT) systems typically apply REID-based paradigm to hold a balance between computational efficiency and performance.

Multi-Object Tracking Multiple Object Tracking

DWM: A Decomposable Winograd Method for Convolution Acceleration

no code implementations3 Feb 2020 Di Huang, Xishan Zhang, Rui Zhang, Tian Zhi, Deyuan He, Jiaming Guo, Chang Liu, Qi Guo, Zidong Du, Shaoli Liu, Tianshi Chen, Yunji Chen

In this paper, we propose a novel Decomposable Winograd Method (DWM), which breaks through the limitation of original Winograd's minimal filtering algorithm to a wide and general convolutions.

Talent Search and Recommendation Systems at LinkedIn: Practical Challenges and Lessons Learned

no code implementations18 Sep 2018 Sahin Cem Geyik, Qi Guo, Bo Hu, Cagri Ozcaglar, Ketan Thakkar, Xianren Wu, Krishnaram Kenthapadi

LinkedIn Talent Solutions business contributes to around 65% of LinkedIn's annual revenue, and provides tools for job providers to reach out to potential candidates and for job seekers to find suitable career opportunities.

Information Retrieval Recommendation Systems

Tackling 3D ToF Artifacts Through Learning and the FLAT Dataset

no code implementations ECCV 2018 Qi Guo, Iuri Frosio, Orazio Gallo, Todd Zickler, Jan Kautz

Scene motion, multiple reflections, and sensor noise introduce artifacts in the depth reconstruction performed by time-of-flight cameras.

BENCHIP: Benchmarking Intelligence Processors

no code implementations23 Oct 2017 Jinhua Tao, Zidong Du, Qi Guo, Huiying Lan, Lei Zhang, Shengyuan Zhou, Lingjie Xu, Cong Liu, Haifeng Liu, Shan Tang, Allen Rush, Willian Chen, Shaoli Liu, Yunji Chen, Tianshi Chen

The variety of emerging intelligence processors requires standard benchmarks for fair comparison and system optimization (in both software and hardware).

Focal Track: Depth and Accommodation With Oscillating Lens Deformation

no code implementations ICCV 2017 Qi Guo, Emma Alexander, Todd Zickler

The focal track sensor is a monocular and computationally efficient depth sensor that is based on defocus controlled by a liquid membrane lens.

Towards thinner convolutional neural networks through Gradually Global Pruning

no code implementations29 Mar 2017 Zhengtao Wang, Ce Zhu, Zhiqiang Xia, Qi Guo, Yipeng Liu

Deep network pruning is an effective method to reduce the storage and computation cost of deep neural networks when applying them to resource-limited devices.

Network Pruning

Attribute-controlled face photo synthesis from simple line drawing

no code implementations9 Feb 2017 Qi Guo, Ce Zhu, Zhiqiang Xia, Zhengtao Wang, Yipeng Liu

In this paper, we propose a deep generative model to synthesize face photo from simple line drawing controlled by face attributes such as hair color and complexion.

Every Filter Extracts A Specific Texture In Convolutional Neural Networks

1 code implementation15 Aug 2016 Zhiqiang Xia, Ce Zhu, Zhengtao Wang, Qi Guo, Yipeng Liu

We also demonstrate that style of images could be a combination of these texture primitives.

A Generic Inverted Index Framework for Similarity Search on the GPU - Technical Report

1 code implementation28 Mar 2016 Jingbo Zhou, Qi Guo, H. V. Jagadish, Luboš Krčál, Siyuan Liu, Wenhao Luan, Anthony K. H. Tung, Yueji Yang, Yuxin Zheng

We propose a novel generic inverted index framework on the GPU (called GENIE), aiming to reduce the programming complexity of the GPU for parallel similarity search of different data types.

Sliding-Window Optimization on an Ambiguity-Clearness Graph for Multi-object Tracking

no code implementations28 Nov 2015 Qi Guo, Le Dan, Dong Yin, Xiangyang Ji

Multi-object tracking remains challenging due to frequent occurrence of occlusions and outliers.

Multi-Object Tracking

Intelligent Health Recommendation System for Computer Users

no code implementations29 Apr 2015 Qi Guo, Zixuan Wang, Ming Li, Hamid Aghajan

The time people spend in front of computers has been increasing steadily due to the role computers play in modern society.

Efficient Divide-And-Conquer Classification Based on Feature-Space Decomposition

no code implementations29 Jan 2015 Qi Guo, Bo-Wei Chen, Feng Jiang, Xiangyang Ji, Sun-Yuan Kung

Firstly, we divide the feature space into several subspaces using the decomposition method proposed in this paper.

General Classification

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