Search Results for author: Yao Lu

Found 74 papers, 25 papers with code

Exploring Inductive Biases in Contrastive Learning: A Clustering Perspective

no code implementations17 May 2023 Yunzhe Zhang, Yao Lu, Lei Xu, Kunlin Yang, Hui Tang, Shuyuan Ye, Qi Xuan

This paper investigates the differences in data organization between contrastive and supervised learning methods, focusing on the concept of locally dense clusters.

Contrastive Learning

Spatiotemporal and Semantic Zero-inflated Urban Anomaly Prediction

no code implementations4 Apr 2023 Yao Lu, Pengyuan Zhou, Yong Liao, Haiyong Xie

Urban anomaly predictions, such as traffic accident prediction and crime prediction, are of vital importance to smart city security and maintenance.

Crime Prediction STS

SR-init: An interpretable layer pruning method

1 code implementation14 Mar 2023 Hui Tang, Yao Lu, Qi Xuan

Our SR-init method is inspired by the discovery that the accuracy drop due to stochastic re-initialization of layer parameters differs in various layers.

Open-World Object Manipulation using Pre-trained Vision-Language Models

no code implementations2 Mar 2023 Austin Stone, Ted Xiao, Yao Lu, Keerthana Gopalakrishnan, Kuang-Huei Lee, Quan Vuong, Paul Wohlhart, Brianna Zitkovich, Fei Xia, Chelsea Finn, Karol Hausman

This brings up a notably difficult challenge for robots: while robot learning approaches allow robots to learn many different behaviors from first-hand experience, it is impractical for robots to have first-hand experiences that span all of this semantic information.

Language Modelling

Grounded Decoding: Guiding Text Generation with Grounded Models for Robot Control

no code implementations1 Mar 2023 Wenlong Huang, Fei Xia, Dhruv Shah, Danny Driess, Andy Zeng, Yao Lu, Pete Florence, Igor Mordatch, Sergey Levine, Karol Hausman, Brian Ichter

Recent progress in large language models (LLMs) has demonstrated the ability to learn and leverage Internet-scale knowledge through pre-training with autoregressive models.

Language Modelling Text Generation

Joint Optimization of Base Station Clustering and Service Caching in User-Centric MEC

1 code implementation21 Feb 2023 Langtian Qin, Hancheng Lu, Yao Lu, Chenwu Zhang, Feng Wu

To address single-base station (BS) transmission limitation and serious edge effect in traditional cellular-based edge service caching networks, in this paper, we proposed a novel user-centric edge service caching framework where each user is jointly provided with edge caching and wireless transmission services by a specific BS cluster instead of a single BS.

Egocentric Hand-object Interaction Detection

no code implementations16 Nov 2022 Yao Lu, Yanan Liu

In this paper, we propose a method to jointly determine the status of hand-object interaction.

Hand Pose Estimation

Token Turing Machines

1 code implementation CVPR 2023 Michael S. Ryoo, Keerthana Gopalakrishnan, Kumara Kahatapitiya, Ted Xiao, Kanishka Rao, Austin Stone, Yao Lu, Julian Ibarz, Anurag Arnab

The model's memory module ensures that a new observation will only be processed with the contents of the memory (and not the entire history), meaning that it can efficiently process long sequences with a bounded computational cost at each step.

Action Detection Activity Detection

Robotic Table Wiping via Reinforcement Learning and Whole-body Trajectory Optimization

no code implementations19 Oct 2022 Thomas Lew, Sumeet Singh, Mario Prats, Jeffrey Bingham, Jonathan Weisz, Benjie Holson, Xiaohan Zhang, Vikas Sindhwani, Yao Lu, Fei Xia, Peng Xu, Tingnan Zhang, Jie Tan, Montserrat Gonzalez

This problem is challenging, as it requires planning wiping actions while reasoning over uncertain latent dynamics of crumbs and spills captured via high-dimensional visual observations.

reinforcement-learning Reinforcement Learning (RL)

PI-QT-Opt: Predictive Information Improves Multi-Task Robotic Reinforcement Learning at Scale

no code implementations15 Oct 2022 Kuang-Huei Lee, Ted Xiao, Adrian Li, Paul Wohlhart, Ian Fischer, Yao Lu

The predictive information, the mutual information between the past and future, has been shown to be a useful representation learning auxiliary loss for training reinforcement learning agents, as the ability to model what will happen next is critical to success on many control tasks.

reinforcement-learning Reinforcement Learning (RL) +2

Low Error-Rate Approximate Multiplier Design for DNNs with Hardware-Driven Co-Optimization

no code implementations8 Oct 2022 Yao Lu, Jide Zhang, Su Zheng, Zhen Li, Lingli Wang

In this paper, two approximate 3*3 multipliers are proposed and the synthesis results of the ASAP-7nm process library justify that they can reduce the area by 31. 38% and 36. 17%, and the power consumption by 36. 73% and 35. 66% compared with the exact multiplier, respectively.

The least-used key selection method for information retrieval in large-scale Cloud-based service repositories

no code implementations16 Aug 2022 Jiayan Gu, Ashiq Anjum, Yan Wu, Lu Liu, John Panneerselvam, Yao Lu, Bo Yuan

The experimental results show that the proposed least-used key selection method improves the service retrieval efficiency significantly compared with the designated key selection method in the case of the unequal appearing probability of parameters in service retrieval requests under three indexing models.

Information Retrieval Management +1

SeeFar: Vehicle Speed Estimation and Flow Analysis from a Moving UAV

no code implementations ICIAP 2022 Mang Ning, Xiaoliang Ma, Yao Lu, Simone Calderara, Rita Cucchiara

In this paper, we introduce SeeFar to achieve vehicle speed estimation and traffic flow analysis based on YOLOv5 and DeepSORT from a moving drone.

Vehicle Speed Estimation

Serving and Optimizing Machine Learning Workflows on Heterogeneous Infrastructures

no code implementations10 May 2022 Yongji Wu, Matthew Lentz, Danyang Zhuo, Yao Lu

With the advent of ubiquitous deployment of smart devices and the Internet of Things, data sources for machine learning inference have increasingly moved to the edge of the network.

AutoML BIG-bench Machine Learning +5

Jump-Start Reinforcement Learning

no code implementations5 Apr 2022 Ikechukwu Uchendu, Ted Xiao, Yao Lu, Banghua Zhu, Mengyuan Yan, Joséphine Simon, Matthew Bennice, Chuyuan Fu, Cong Ma, Jiantao Jiao, Sergey Levine, Karol Hausman

In addition, we provide an upper bound on the sample complexity of JSRL and show that with the help of a guide-policy, one can improve the sample complexity for non-optimism exploration methods from exponential in horizon to polynomial.

reinforcement-learning Reinforcement Learning (RL)

On-Sensor Binarized Fully Convolutional Neural Network with A Pixel Processor Array

no code implementations2 Feb 2022 Yanan Liu, Laurie Bose, Yao Lu, Piotr Dudek, Walterio Mayol-Cuevas

This work presents a method to implement fully convolutional neural networks (FCNs) on Pixel Processor Array (PPA) sensors, and demonstrates coarse segmentation and object localisation tasks.

Binarization Semantic Segmentation

HEAM: High-Efficiency Approximate Multiplier Optimization for Deep Neural Networks

2 code implementations20 Jan 2022 Su Zheng, Zhen Li, Yao Lu, Jingbo Gao, Jide Zhang, Lingli Wang

We propose an optimization method for the automatic design of approximate multipliers, which minimizes the average error according to the operand distributions.

Quantization Vocal Bursts Intensity Prediction

Detail-Preserving Transformer for Light Field Image Super-Resolution

1 code implementation2 Jan 2022 Shunzhou Wang, Tianfei Zhou, Yao Lu, Huijun Di

DPT consists of two branches, with each associated with a Transformer for learning from an original or gradient image sequence.

Image Super-Resolution

Delayed Gradient Averaging: Tolerate the Communication Latency for Federated Learning

no code implementations NeurIPS 2021 Ligeng Zhu, Hongzhou Lin, Yao Lu, Yujun Lin, Song Han

Federated Learning is an emerging direction in distributed machine learning that en-ables jointly training a model without sharing the data.

Federated Learning

Understanding the Dynamics of DNNs Using Graph Modularity

1 code implementation24 Nov 2021 Yao Lu, Wen Yang, Yunzhe Zhang, Zuohui Chen, Jinyin Chen, Qi Xuan, Zhen Wang, Xiaoniu Yang

Specifically, we model the process of class separation of intermediate representations in pre-trained DNNs as the evolution of communities in dynamic graphs.

Feature Engineering

Graph-Based Similarity of Neural Network Representations

1 code implementation22 Nov 2021 Zuohui Chen, Yao Lu, Jinxuan Hu, Wen Yang, Qi Xuan, Zhen Wang, Xiaoniu Yang

Understanding the black-box representations in Deep Neural Networks (DNN) is an essential problem in deep learning.

RGP: Neural Network Pruning through Its Regular Graph Structure

no code implementations28 Oct 2021 Zhuangzhi Chen, Jingyang Xiang, Yao Lu, Qi Xuan, Xiaoniu Yang

In this paper, we study the graph structure of the neural network, and propose regular graph based pruning (RGP) to perform a one-shot neural network pruning.

Network Pruning

The Object at Hand: Automated Editing for Mixed Reality Video Guidance from Hand-Object Interactions

no code implementations29 Sep 2021 Yao Lu, Walterio W. Mayol-Cuevas

In this paper, we concern with the problem of how to automatically extract the steps that compose real-life hand activities.

Mixed Reality

Understanding Egocentric Hand-Object Interactions from Hand Pose Estimation

no code implementations29 Sep 2021 Yao Lu, Walterio W. Mayol-Cuevas

To show the ability to preserve the semantic information of our method, we also report the performance of grasp type classification on GUN-71 dataset and outperforms the benchmark by only using the predicted 3-d hand pose.

Hand Pose Estimation

Egocentric Hand-object Interaction Detection and Application

no code implementations29 Sep 2021 Yao Lu, Walterio W. Mayol-Cuevas

We compare our method with the most recent work from Shan et al. \cite{Shan20} on selected images from EPIC-KITCHENS \cite{damen2018scaling} dataset and achieve $89\%$ accuracy on HOI (hand-object interaction) detection which is comparative to Shan's ($92\%$).

Deep 3D-CNN for Depression Diagnosis with Facial Video Recording of Self-Rating Depression Scale Questionnaire

no code implementations22 Jul 2021 Wanqing Xie, Lizhong Liang, Yao Lu, Hui Luo, Xiaofeng Liu

The superior performance of our system shows the validity of combining facial video recording with the SDS score for more accurate self-diagnose.

S2Looking: A Satellite Side-Looking Dataset for Building Change Detection

1 code implementation20 Jul 2021 Li Shen, Yao Lu, Hao Chen, Hao Wei, Donghai Xie, Jiabao Yue, Rui Chen, Shouye Lv, Bitao Jiang

This paper therefore introduces S2Looking, a building-change-detection dataset that contains large-scale side-looking satellite images captured at various off-nadir angles.

Change Detection Management

Interpreting Depression From Question-wise Long-term Video Recording of SDS Evaluation

no code implementations25 Jun 2021 Wanqing Xie, Lizhong Liang, Yao Lu, Chen Wang, Jihong Shen, Hui Luo, Xiaofeng Liu

To automatically interpret depression from the SDS evaluation and the paired video, we propose an end-to-end hierarchical framework for the long-term variable-length video, which is also conditioned on the questionnaire results and the answering time.

Depression Detection

Adversarial Sample Detection via Channel Pruning

no code implementations ICML Workshop AML 2021 Zuohui Chen, Renxuan Wang, Yao Lu, Jingyang Xiang, Qi Xuan

Experiments on CIFAR10 and SVHN show that the FLOPs and size of our generated model are only 24. 46\% and 4. 86\% of the original model.

Optimization of Service Addition in Multilevel Index Model for Edge Computing

no code implementations8 Jun 2021 Jiayan Gu, Yan Wu, Ashiq Anjum, John Panneerselvam, Yao Lu, Bo Yuan

With the development of Edge Computing and Artificial Intelligence (AI) technologies, edge devices are witnessed to generate data at unprecedented volume.

Edge-computing Retrieval

ISTR: End-to-End Instance Segmentation with Transformers

1 code implementation3 May 2021 Jie Hu, Liujuan Cao, Yao Lu, Shengchuan Zhang, Yan Wang, Ke Li, Feiyue Huang, Ling Shao, Rongrong Ji

However, such an upgrade is not applicable to instance segmentation, due to its significantly higher output dimensions compared to object detection.

Instance Segmentation object-detection +2

Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity

1 code implementation ACL 2022 Yao Lu, Max Bartolo, Alastair Moore, Sebastian Riedel, Pontus Stenetorp

When primed with only a handful of training samples, very large, pretrained language models such as GPT-3 have shown competitive results when compared to fully-supervised, fine-tuned, large, pretrained language models.

text-classification Text Classification

Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills

no code implementations15 Apr 2021 Yevgen Chebotar, Karol Hausman, Yao Lu, Ted Xiao, Dmitry Kalashnikov, Jake Varley, Alex Irpan, Benjamin Eysenbach, Ryan Julian, Chelsea Finn, Sergey Levine

We consider the problem of learning useful robotic skills from previously collected offline data without access to manually specified rewards or additional online exploration, a setting that is becoming increasingly important for scaling robot learning by reusing past robotic data.

Q-Learning reinforcement-learning +1

Zeus: Efficiently Localizing Actions in Videos using Reinforcement Learning

no code implementations6 Apr 2021 Pramod Chunduri, Jaeho Bang, Yao Lu, Joy Arulraj

ZEUS trains a reinforcement learning agent that learns to adaptively modify the input video segments that are subsequently sent to an action classification network.

Action Classification Action Detection +3

Learning to Estimate Hidden Motions with Global Motion Aggregation

2 code implementations ICCV 2021 Shihao Jiang, Dylan Campbell, Yao Lu, Hongdong Li, Richard Hartley

We demonstrate that the optical flow estimates in the occluded regions can be significantly improved without damaging the performance in non-occluded regions.

Optical Flow Estimation

Learning Optical Flow from a Few Matches

1 code implementation CVPR 2021 Shihao Jiang, Yao Lu, Hongdong Li, Richard Hartley

In this paper, we show that the dense correlation volume representation is redundant and accurate flow estimation can be achieved with only a fraction of elements in it.

Optical Flow Estimation

Visionary: Vision architecture discovery for robot learning

no code implementations26 Mar 2021 Iretiayo Akinola, Anelia Angelova, Yao Lu, Yevgen Chebotar, Dmitry Kalashnikov, Jacob Varley, Julian Ibarz, Michael S. Ryoo

We propose a vision-based architecture search algorithm for robot manipulation learning, which discovers interactions between low dimension action inputs and high dimensional visual inputs.

Neural Architecture Search Robot Manipulation

Disentangle Perceptual Learning through Online Contrastive Learning

no code implementations24 Jun 2020 Kangfu Mei, Yao Lu, Qiaosi Yi, Hao-Yu Wu, Juncheng Li, Rui Huang

Perceptual learning approaches like perceptual loss are empirically powerful for such tasks but they usually rely on the pre-trained classification network to provide features, which are not necessarily optimal in terms of visual perception of image transformation.

Contrastive Learning feature selection

Bidirectionally Self-Normalizing Neural Networks

no code implementations22 Jun 2020 Yao Lu, Stephen Gould, Thalaiyasingam Ajanthan

The problem of vanishing and exploding gradients has been a long-standing obstacle that hinders the effective training of neural networks.

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

MedSRGAN: medical images super-resolution using generative adversarial networks

1 code implementation Springer 2020 Yuchong Gu, Zitao Zen, Haibin Chen, Jun Wei, Yaqin Zhang, Binghui Chen, Yingqin Li, Yujuan Qin, Qing Xie, Zhuoren Jiang, Yao Lu

Super-resolution (SR) in medical imaging is an emerging application in medical imaging due to the needs of high quality images acquired with limited radiation dose, such as low dose Computer Tomography (CT), low field magnetic resonance imaging (MRI).


Natural Language Generation for Effective Knowledge Distillation

1 code implementation WS 2019 Raphael Tang, Yao Lu, Jimmy Lin

Knowledge distillation can effectively transfer knowledge from BERT, a deep language representation model, to traditional, shallow word embedding-based neural networks, helping them approach or exceed the quality of other heavyweight language representation models.

Knowledge Distillation Linguistic Acceptability +5

Decoding of visual-related information from the human EEG using an end-to-end deep learning approach

no code implementations1 Nov 2019 Lingling Yang, Leanne Lai Hang Chan, Yao Lu

Here, we proposed a CNNLSTM based neural network architecture termed EEG_CNNLSTMNet for the classification of EEG signals in response to grating stimuli with different spatial frequencies.

Electroencephalogram (EEG) General Classification +1

Prediction Modeling and Analysis for Telecom Customer Churn in Two Months

no code implementations1 Nov 2019 Lingling Yang, Dongyang Li, Yao Lu

In this paper, we propose a new T+2 churn customer prediction model, in which the churn customers in two months are recognized and the one-month window T+1 is reserved to carry out churn management strategies.

Management Vocal Bursts Valence Prediction

Distributed Training Across the World

no code implementations25 Sep 2019 Ligeng Zhu, Yao Lu, Yujun Lin, Song Han

Traditional synchronous distributed training is performed inside a cluster, since it requires high bandwidth and low latency network (e. g. 25Gb Ethernet or Infini-band).

Mobile Video Action Recognition

no code implementations27 Aug 2019 Yuqi Huo, Xiaoli Xu, Yao Lu, Yulei Niu, Zhiwu Lu, Ji-Rong Wen

In addition to motion vectors, we also provide a temporal fusion method to explicitly induce the temporal context.

Action Recognition Temporal Action Localization

Predictive Ensemble Learning with Application to Scene Text Detection

no code implementations12 May 2019 Danlu Chen, Xu-Yao Zhang, Wei zhang, Yao Lu, Xiuli Li, Tao Mei

Taking scene text detection as the application, where no suitable ensemble learning strategy exists, PEL can significantly improve the performance, compared to either individual state-of-the-art models, or the fusion of multiple models by non-maximum suppression.

Classification Ensemble Learning +4

Cross-language Citation Recommendation via Hierarchical Representation Learning on Heterogeneous Graph

1 code implementation31 Dec 2018 Zhuoren Jiang, Yue Yin, Liangcai Gao, Yao Lu, Xiaozhong Liu

While the volume of scholarly publications has increased at a frenetic pace, accessing and consuming the useful candidate papers, in very large digital libraries, is becoming an essential and challenging task for scholars.

Citation Recommendation Representation Learning

Crowd Counting with Density Adaption Networks

no code implementations26 Jun 2018 Li Wang, Weiyuan Shao, Yao Lu, Hao Ye, Jian Pu, Yingbin Zheng

Crowd counting is one of the core tasks in various surveillance applications.

Crowd Counting

Block Mean Approximation for Efficient Second Order Optimization

no code implementations16 Apr 2018 Yao Lu, Mehrtash Harandi, Richard Hartley, Razvan Pascanu

Advanced optimization algorithms such as Newton method and AdaGrad benefit from second order derivative or second order statistics to achieve better descent directions and faster convergence rates.

An interpretable LSTM neural network for autoregressive exogenous model

no code implementations14 Apr 2018 Tian Guo, Tao Lin, Yao Lu

In this paper, we propose an interpretable LSTM recurrent neural network, i. e., multi-variable LSTM for time series with exogenous variables.

Time Series Analysis

Precise Temporal Action Localization by Evolving Temporal Proposals

no code implementations13 Apr 2018 Haonan Qiu, Yingbin Zheng, Hao Ye, Yao Lu, Feng Wang, Liang He

The performances of existing action localization approaches remain unsatisfactory in precisely determining the beginning and the end of an action.

Temporal Action Localization

Devon: Deformable Volume Network for Learning Optical Flow

no code implementations20 Feb 2018 Yao Lu, Jack Valmadre, Heng Wang, Juho Kannala, Mehrtash Harandi, Philip H. S. Torr

State-of-the-art neural network models estimate large displacement optical flow in multi-resolution and use warping to propagate the estimation between two resolutions.

Optical Flow Estimation

Generative Adversarial Network for Abstractive Text Summarization

1 code implementation26 Nov 2017 Linqing Liu, Yao Lu, Min Yang, Qiang Qu, Jia Zhu, Hongyan Li

In this paper, we propose an adversarial process for abstractive text summarization, in which we simultaneously train a generative model G and a discriminative model D. In particular, we build the generator G as an agent of reinforcement learning, which takes the raw text as input and predicts the abstractive summarization.

Abstractive Text Summarization reinforcement-learning +1

Doubly Stochastic Neighbor Embedding on Spheres

1 code implementation7 Sep 2016 Yao Lu, Jukka Corander, Zhirong Yang

To solve this problem, we introduce a fast normalization method and normalize the similarity matrix to be doubly stochastic such that all the data points have equal total similarities.

Data Visualization

Contour Flow: Middle-Level Motion Estimation by Combining Motion Segmentation and Contour Alignment

no code implementations ICCV 2015 Huijun Di, Qingxuan Shi, Feng Lv, Ming Qin, Yao Lu

Our goal is to estimate contour flow (the contour pairs with consistent point correspondence) from inconsistent contours extracted independently in two video frames.

Motion Estimation Motion Segmentation +1

Unsupervised Learning on Neural Network Outputs: with Application in Zero-shot Learning

1 code implementation2 Jun 2015 Yao Lu

The outputs of a trained neural network contain much richer information than just an one-hot classifier.

Zero-Shot Learning

Instance Significance Guided Multiple Instance Boosting for Robust Visual Tracking

no code implementations19 Jan 2015 Jinwu Liu, Yao Lu, Tianfei Zhou

Multiple Instance Learning (MIL) recently provides an appealing way to alleviate the drifting problem in visual tracking.

Multiple Instance Learning Visual Tracking

Abrupt Motion Tracking via Nearest Neighbor Field Driven Stochastic Sampling

no code implementations28 Oct 2014 Tianfei Zhou, Yao Lu, Feng Lv, Huijun Di, Qingjie Zhao, Jian Zhang

Stochastic sampling based trackers have shown good performance for abrupt motion tracking so that they have gained popularity in recent years.

Motion Detection

A Fast Projected Fixed-Point Algorithm for Large Graph Matching

1 code implementation3 Jul 2012 Yao Lu, Kai-Zhu Huang, Cheng-Lin Liu

In particular, with high accuracy, our algorithm takes only a few seconds (in a PC) to match two graphs of 1, 000 nodes.

Graph Matching

Correlative Multi-Label Multi-Instance Image Annotation

no code implementations IEEE International Conference on Computer Vision 2011 Xiangyang Xue, Wei zhang, Jie Zhang, Bin Wu, Jianping Fan, Yao Lu

The cross-level label coherence en-codes the consistency between the labels at the image leveland the labels at the region level.

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