Search Results for author: Jie Liu

Found 154 papers, 53 papers with code

Topology Imbalance and Relation Inauthenticity Aware Hierarchical Graph Attention Networks for Fake News Detection

no code implementations COLING 2022 Li Gao, Lingyun Song, Jie Liu, Bolin Chen, Xuequn Shang

However, little attention is paid to the issues of both authenticity of the relationships and topology imbalance in the structure of NPG, which trick existing methods and thus lead to incorrect prediction results.

Fake News Detection Graph Attention +1

Spatial-temporal Memories Enhanced Graph Autoencoder for Anomaly Detection in Dynamic Graphs

no code implementations14 Mar 2024 Jie Liu, Xuequn Shang, Xiaolin Han, Wentao Zhang, Hongzhi Yin

Then STRIPE incorporates separate spatial and temporal memory networks, which capture and store prototypes of normal patterns, thereby preserving the uniqueness of spatial and temporal normality.

Anomaly Detection

UniSparse: An Intermediate Language for General Sparse Format Customization

1 code implementation9 Mar 2024 Jie Liu, Zhongyuan Zhao, Zijian Ding, Benjamin Brock, Hongbo Rong, Zhiru Zhang

The ongoing trend of hardware specialization has led to a growing use of custom data formats when processing sparse workloads, which are typically memory-bound.

Attribute Code Generation

An EnKF-LSTM Assimilation Algorithm for Crop Growth Model

no code implementations6 Mar 2024 SiQi Zhou, Ling Wang, Jie Liu, Jinshan Tang

However, there are large difference between the simulation results obtained by the crop models and the actual results, thus in this paper, we proposed to combine the simulation results with the collected crop data for data assimilation so that the accuracy of prediction will be improved.

AlignMiF: Geometry-Aligned Multimodal Implicit Field for LiDAR-Camera Joint Synthesis

1 code implementation27 Feb 2024 Tao Tang, Guangrun Wang, Yixing Lao, Peng Chen, Jie Liu, Liang Lin, Kaicheng Yu, Xiaodan Liang

Through extensive experiments across various datasets and scenes, we demonstrate the effectiveness of our approach in facilitating better interaction between LiDAR and camera modalities within a unified neural field.

Novel View Synthesis

MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues

no code implementations22 Feb 2024 Ge Bai, Jie Liu, Xingyuan Bu, Yancheng He, Jiaheng Liu, Zhanhui Zhou, Zhuoran Lin, Wenbo Su, Tiezheng Ge, Bo Zheng, Wanli Ouyang

By conducting a detailed analysis of real multi-turn dialogue data, we construct a three-tier hierarchical ability taxonomy comprising 4208 turns across 1388 multi-turn dialogues in 13 distinct tasks.

ConceptMath: A Bilingual Concept-wise Benchmark for Measuring Mathematical Reasoning of Large Language Models

1 code implementation22 Feb 2024 Yanan Wu, Jie Liu, Xingyuan Bu, Jiaheng Liu, Zhanhui Zhou, Yuanxing Zhang, Chenchen Zhang, Zhiqi Bai, Haibin Chen, Tiezheng Ge, Wanli Ouyang, Wenbo Su, Bo Zheng

This paper introduces ConceptMath, a bilingual (English and Chinese), fine-grained benchmark that evaluates concept-wise mathematical reasoning of Large Language Models (LLMs).

Math Mathematical Reasoning

GCOF: Self-iterative Text Generation for Copywriting Using Large Language Model

no code implementations21 Feb 2024 Jianghui Zhou, Ya Gao, Jie Liu, Xuemin Zhao, Zhaohua Yang, Yue Wu, Lirong Shi

Large language models(LLM) such as ChatGPT have substantially simplified the generation of marketing copy, yet producing content satisfying domain specific requirements, such as effectively engaging customers, remains a significant challenge.

Feature Engineering Language Modelling +3

OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems

1 code implementation21 Feb 2024 Chaoqun He, Renjie Luo, Yuzhuo Bai, Shengding Hu, Zhen Leng Thai, Junhao Shen, Jinyi Hu, Xu Han, Yujie Huang, Yuxiang Zhang, Jie Liu, Lei Qi, Zhiyuan Liu, Maosong Sun

Notably, the best-performing model, GPT-4V, attains an average score of 17. 23% on OlympiadBench, with a mere 11. 28% in physics, highlighting the benchmark rigor and the intricacy of physical reasoning.

Logical Fallacies

Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!

1 code implementation19 Feb 2024 Zhanhui Zhou, Jie Liu, Zhichen Dong, Jiaheng Liu, Chao Yang, Wanli Ouyang, Yu Qiao

Large language models (LLMs) need to undergo safety alignment to ensure safe conversations with humans.

Language Modelling

Asclepius: A Spectrum Evaluation Benchmark for Medical Multi-Modal Large Language Models

no code implementations17 Feb 2024 Wenxuan Wang, Yihang Su, Jingyuan Huan, Jie Liu, WenTing Chen, Yudi Zhang, Cheng-Yi Li, Kao-Jung Chang, Xiaohan Xin, Linlin Shen, Michael R. Lyu

However, these models are often evaluated on benchmarks that are unsuitable for the Med-MLLMs due to the intricate nature of the real-world diagnostic frameworks, which encompass diverse medical specialties and involve complex clinical decisions.

Dynamic Prototype Adaptation with Distillation for Few-shot Point Cloud Segmentation

no code implementations29 Jan 2024 Jie Liu, Wenzhe Yin, Haochen Wang, Yunlu Chen, Jan-Jakob Sonke, Efstratios Gavves

Existing prototype-based methods rely on support prototypes to guide the segmentation of query point clouds, but they encounter challenges when significant object variations exist between the support prototypes and query features.

Point Cloud Segmentation Transfer Learning

Sketch and Refine: Towards Fast and Accurate Lane Detection

no code implementations26 Jan 2024 Chao Chen, Jie Liu, Chang Zhou, Jie Tang, Gangshan Wu

At the "Sketch" stage, local directions of keypoints can be easily estimated by fast convolutional layers.

Lane Detection

Topology Learning for Heterogeneous Decentralized Federated Learning over Unreliable D2D Networks

no code implementations21 Dec 2023 Zheshun Wu, Zenglin Xu, Dun Zeng, Junfan Li, Jie Liu

To address these challenges, we conduct a thorough theoretical convergence analysis for DFL and derive a convergence bound.

Federated Learning

Short-Term Multi-Horizon Line Loss Rate Forecasting of a Distribution Network Using Attention-GCN-LSTM

no code implementations19 Dec 2023 Jie Liu, Yijia Cao, Yong Li, Yixiu Guo, Wei Deng

Accurately predicting line loss rates is vital for effective line loss management in distribution networks, especially over short-term multi-horizons ranging from one hour to one week.

Management

A Perspective of Q-value Estimation on Offline-to-Online Reinforcement Learning

1 code implementation12 Dec 2023 Yinmin Zhang, Jie Liu, Chuming Li, Yazhe Niu, Yaodong Yang, Yu Liu, Wanli Ouyang

In this paper, from a novel perspective, we systematically study the challenges that remain in O2O RL and identify that the reason behind the slow improvement of the performance and the instability of online finetuning lies in the inaccurate Q-value estimation inherited from offline pretraining.

Offline RL

EdgeConvFormer: Dynamic Graph CNN and Transformer based Anomaly Detection in Multivariate Time Series

no code implementations4 Dec 2023 Jie Liu, Qilin Li, Senjian An, Bradley Ezard, Ling Li

Transformer-based models for anomaly detection in multivariate time series can benefit from the self-attention mechanism due to its advantage in modeling long-term dependencies.

Anomaly Detection Time Series

Information-Theoretic Generalization Analysis for Topology-aware Heterogeneous Federated Edge Learning over Noisy Channels

no code implementations25 Oct 2023 Zheshun Wu, Zenglin Xu, Hongfang Yu, Jie Liu

In FEEL, both mobile devices transmitting model parameters over noisy channels and collecting data in diverse environments pose challenges to the generalization of trained models.

Federated Learning

Distance-rank Aware Sequential Reward Learning for Inverse Reinforcement Learning with Sub-optimal Demonstrations

no code implementations13 Oct 2023 Lu Li, Yuxin Pan, RuoBing Chen, Jie Liu, Zilin Wang, Yu Liu, Zhiheng Li

Considering that obtaining expert demonstrations can be costly, the focus of current IRL techniques is on learning a better-than-demonstrator policy using a reward function derived from sub-optimal demonstrations.

Contrastive Learning

Advocating for the Silent: Enhancing Federated Generalization for Non-Participating Clients

no code implementations11 Oct 2023 Zheshun Wu, Zenglin Xu, Dun Zeng, Qifan Wang, Jie Liu

Federated Learning (FL) has surged in prominence due to its capability of collaborative model training without direct data sharing.

Federated Learning Generalization Bounds

Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization

1 code implementation5 Oct 2023 Zhanhui Zhou, Jie Liu, Chao Yang, Jing Shao, Yu Liu, Xiangyu Yue, Wanli Ouyang, Yu Qiao

A single language model (LM), despite aligning well with an average labeler through reinforcement learning from human feedback (RLHF), may not universally suit diverse human preferences.

Language Modelling Long Form Question Answering

SSHR: Leveraging Self-supervised Hierarchical Representations for Multilingual Automatic Speech Recognition

no code implementations29 Sep 2023 Hongfei Xue, Qijie Shao, Kaixun Huang, Peikun Chen, Lei Xie, Jie Liu

We first analyze the different layers of the SSL model for language-related and content-related information, uncovering layers that show a stronger correlation.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Proposing an intelligent mesh smoothing method with graph neural networks

no code implementations24 Sep 2023 Zhichao Wang, Xinhai Chen, Junjun Yan, Jie Liu

With a lightweight model, GMSNet can effectively smoothing mesh nodes with varying degrees and remain unaffected by the order of input data.

Data Augmentation

Multi-Modal Automatic Prosody Annotation with Contrastive Pretraining of SSWP

1 code implementation11 Sep 2023 Jinzuomu Zhong, Yang Li, Hui Huang, Jie Liu, Zhiba Su, Jing Guo, Benlai Tang, Fengjie Zhu

While human prosody annotation contributes a lot to the performance, it is a labor-intensive and time-consuming process, often resulting in inconsistent outcomes.

Robust Object Modeling for Visual Tracking

1 code implementation ICCV 2023 Yidong Cai, Jie Liu, Jie Tang, Gangshan Wu

To enjoy the merits of both methods, we propose a robust object modeling framework for visual tracking (ROMTrack), which simultaneously models the inherent template and the hybrid template features.

Object Visual Tracking

Flashlight Search Medial Axis: A Pixel-Free Pore-Network Extraction Algorithm

no code implementations5 Aug 2023 Jie Liu, Tao Zhang, Shuyu Sun

In this way, computational complexity of this method is greatly reduced compared to that of traditional pixel-based extraction methods, thus enabling large-scale pore-network extraction.

Dimensionality Reduction

Lightweight Super-Resolution Head for Human Pose Estimation

1 code implementation31 Jul 2023 Haonan Wang, Jie Liu, Jie Tang, Gangshan Wu

We first propose the SR head, which predicts heatmaps with a spatial resolution higher than the input feature maps (or even consistent with the input image) by super-resolution, to effectively reduce the quantization error and the dependence on further post-processing.

Pose Estimation Quantization +1

BOURNE: Bootstrapped Self-supervised Learning Framework for Unified Graph Anomaly Detection

no code implementations28 Jul 2023 Jie Liu, Mengting He, Xuequn Shang, Jieming Shi, Bin Cui, Hongzhi Yin

By swapping the context embeddings between nodes and edges and measuring the agreement in the embedding space, we enable the mutual detection of node and edge anomalies.

CoLA Contrastive Learning +2

Theoretically Guaranteed Policy Improvement Distilled from Model-Based Planning

no code implementations24 Jul 2023 Chuming Li, Ruonan Jia, Jie Liu, Yinmin Zhang, Yazhe Niu, Yaodong Yang, Yu Liu, Wanli Ouyang

Model-based reinforcement learning (RL) has demonstrated remarkable successes on a range of continuous control tasks due to its high sample efficiency.

Continuous Control Model-based Reinforcement Learning +1

Auxiliary-Tasks Learning for Physics-Informed Neural Network-Based Partial Differential Equations Solving

1 code implementation12 Jul 2023 Junjun Yan, Xinhai Chen, Zhichao Wang, Enqiang Zhou, Jie Liu

To alleviate these issues, we proposed auxiliary-task learning-based physics-informed neural networks (ATL-PINNs), which provide four different auxiliary-task learning modes and investigate their performance compared with original PINNs.

Machine Learning Study of the Extended Drug-target Interaction Network informed by Pain Related Voltage-Gated Sodium Channels

1 code implementation11 Jul 2023 Long Chen, Jian Jiang, Bozheng Dou, Hongsong Feng, Jie Liu, Yueying Zhu, Bengong Zhang, Tianshou Zhou, Guo-Wei Wei

Pain is a significant global health issue, and the current treatment options for pain management have limitations in terms of effectiveness, side effects, and potential for addiction.

Management

TranssionADD: A multi-frame reinforcement based sequence tagging model for audio deepfake detection

no code implementations27 Jun 2023 Jie Liu, Zhiba Su, Hui Huang, Caiyan Wan, Quanxiu Wang, Jiangli Hong, Benlai Tang, Fengjie Zhu

We propose our novel TranssionADD system as a solution to the challenging problem of model robustness and audio segment outliers in the trace competition.

Data Augmentation DeepFake Detection +1

ST-PINN: A Self-Training Physics-Informed Neural Network for Partial Differential Equations

1 code implementation15 Jun 2023 Junjun Yan, Xinhai Chen, Zhichao Wang, Enqiang Zhoui, Jie Liu

To address the issue of low accuracy and convergence problems of existing PINNs, we propose a self-training physics-informed neural network, ST-PINN.

Pseudo Label Self-Learning

DVFO: Learning-Based DVFS for Energy-Efficient Edge-Cloud Collaborative Inference

no code implementations2 Jun 2023 Ziyang Zhang, Yang Zhao, Huan Li, Changyao Lin, Jie Liu

Due to limited resources on edge and different characteristics of deep neural network (DNN) models, it is a big challenge to optimize DNN inference performance in terms of energy consumption and end-to-end latency on edge devices.

Collaborative Inference

TranUSR: Phoneme-to-word Transcoder Based Unified Speech Representation Learning for Cross-lingual Speech Recognition

no code implementations23 May 2023 Hongfei Xue, Qijie Shao, Peikun Chen, Pengcheng Guo, Lei Xie, Jie Liu

Different from UniSpeech, UniData2vec replaces the quantized discrete representations with continuous and contextual representations from a teacher model for phonetically-aware pre-training.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Hierarchical Aligned Multimodal Learning for NER on Tweet Posts

no code implementations15 May 2023 Peipei Liu, Hong Li, Yimo Ren, Jie Liu, Shuaizong Si, Hongsong Zhu, Limin Sun

Mining structured knowledge from tweets using named entity recognition (NER) can be beneficial for many down stream applications such as recommendation and intention understanding.

named-entity-recognition Named Entity Recognition +2

Efficient Reinforcement Learning for Autonomous Driving with Parameterized Skills and Priors

1 code implementation8 May 2023 Letian Wang, Jie Liu, Hao Shao, Wenshuo Wang, RuoBing Chen, Yu Liu, Steven L. Waslander

Inspired by this, we propose ASAP-RL, an efficient reinforcement learning algorithm for autonomous driving that simultaneously leverages motion skills and expert priors.

Autonomous Driving reinforcement-learning

Data valuation: The partial ordinal Shapley value for machine learning

1 code implementation2 May 2023 Jie Liu, Peizheng Wang, Chao Wu

Data valuation using Shapley value has emerged as a prevalent research domain in machine learning applications.

Abstract Algebra Data Valuation

BCEdge: SLO-Aware DNN Inference Services with Adaptive Batching on Edge Platforms

no code implementations1 May 2023 Ziyang Zhang, Huan Li, Yang Zhao, Changyao Lin, Jie Liu

As deep neural networks (DNNs) are being applied to a wide range of edge intelligent applications, it is critical for edge inference platforms to have both high-throughput and low-latency at the same time.

Scheduling

Video Frame Interpolation with Densely Queried Bilateral Correlation

1 code implementation26 Apr 2023 Chang Zhou, Jie Liu, Jie Tang, Gangshan Wu

To better model correlations and to produce more accurate motion fields, we propose the Densely Queried Bilateral Correlation (DQBC) that gets rid of the receptive field dependency problem and thus is more friendly to small and fast-moving objects.

Motion Estimation Video Frame Interpolation

PiClick: Picking the desired mask in click-based interactive segmentation

1 code implementation23 Apr 2023 Cilin Yan, Haochen Wang, Jie Liu, XiaoLong Jiang, Yao Hu, Xu Tang, Guoliang Kang, Efstratios Gavves

Click-based interactive segmentation aims to generate target masks via human clicking, which facilitates efficient pixel-level annotation and image editing.

Interactive Segmentation Segmentation

MS-LSTM: Exploring Spatiotemporal Multiscale Representations in Video Prediction Domain

no code implementations16 Apr 2023 Zhifeng Ma, Hao Zhang, Jie Liu

The drastic variation of motion in spatial and temporal dimensions makes the video prediction task extremely challenging.

Video Prediction

A Heterogeneous Parallel Non-von Neumann Architecture System for Accurate and Efficient Machine Learning Molecular Dynamics

no code implementations26 Mar 2023 Zhuoying Zhao, Ziling Tan, Pinghui Mo, Xiaonan Wang, Dan Zhao, Xin Zhang, Ming Tao, Jie Liu

This paper proposes a special-purpose system to achieve high-accuracy and high-efficiency machine learning (ML) molecular dynamics (MD) calculations.

Atomic Forces

A Monkey Swing Counting Algorithm Based on Object Detection

no code implementations12 Mar 2023 Hao Chen, Zhe-Ming Lu, Jie Liu

This paper focuses on proposing a deep learning-based monkey swing counting algorithm.

object-detection Object Detection

ESCL: Equivariant Self-Contrastive Learning for Sentence Representations

no code implementations9 Mar 2023 Jie Liu, Yixuan Liu, Xue Han, Chao Deng, Junlan Feng

Previous contrastive learning methods for sentence representations often focus on insensitive transformations to produce positive pairs, but neglect the role of sensitive transformations that are harmful to semantic representations.

Contrastive Learning Multi-Task Learning +2

An Empirical Study of Uniform-Architecture Knowledge Distillation in Document Ranking

no code implementations8 Feb 2023 Xubo Qin, Xiyuan Liu, Xiongfeng Zheng, Jie Liu, Yutao Zhu

Specifically, when the student models are in cross-encoder architecture, a pairwise loss of hard labels is critical for training student models, whereas the distillation objectives of intermediate Transformer layers may hurt performance.

Document Ranking Knowledge Distillation

On the impact of spatial heterogeneity and drift rate in a three-patch two-species Lotka-Volterra competition model over a stream

no code implementations16 Jan 2023 Shanshan Chen, Jie Liu, Yixiang Wu

In this paper, we study a three-patch two-species Lotka-Volterra competition patch model over a stream network.

Evolution of dispersal in advective patchy environments with varying drift rates

no code implementations16 Jan 2023 Shanshan Chen, Jie Liu, Yixiang Wu

In this paper, we study a two stream species Lotka-Volterra competition patch model with the patches aligned along a line.

Few-shot Semantic Segmentation with Support-induced Graph Convolutional Network

no code implementations9 Jan 2023 Jie Liu, Yanqi Bao, Wenzhe Yin, Haochen Wang, Yang Gao, Jan-Jakob Sonke, Efstratios Gavves

However, the appearance variations between objects from the same category could be extremely large, leading to unreliable feature matching and query mask prediction.

Few-Shot Semantic Segmentation

CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection

2 code implementations ICCV 2023 Jie Liu, Yixiao Zhang, Jie-Neng Chen, Junfei Xiao, Yongyi Lu, Bennett A. Landman, Yixuan Yuan, Alan Yuille, Yucheng Tang, Zongwei Zhou

The proposed model is developed from an assembly of 14 datasets, using a total of 3, 410 CT scans for training and then evaluated on 6, 162 external CT scans from 3 additional datasets.

Organ Segmentation Segmentation +1

Adjustment and Alignment for Unbiased Open Set Domain Adaptation

1 code implementation CVPR 2023 Wuyang Li, Jie Liu, Bo Han, Yixuan Yuan

In a nutshell, ANNA consists of Front-Door Adjustment (FDA) to correct the biased learning in the source domain and Decoupled Causal Alignment (DCA) to transfer the model unbiasedly.

Domain Adaptation Model Optimization

CC-FedAvg: Computationally Customized Federated Averaging

no code implementations28 Dec 2022 Hao Zhang, Tingting Wu, Siyao Cheng, Jie Liu

Federated learning (FL) is an emerging paradigm to train model with distributed data from numerous Internet of Things (IoT) devices.

Federated Learning

MSV Challenge 2022: NPU-HC Speaker Verification System for Low-resource Indian Languages

no code implementations30 Nov 2022 Yue Li, Li Zhang, Namin Wang, Jie Liu, Lei Xie

Specifically, the weight transfer fine-tuning aims to constrain the distance of the weights between the pre-trained model and the fine-tuned model, which takes advantage of the previously acquired discriminative ability from the large-scale out-domain datasets and avoids catastrophic forgetting and overfitting at the same time.

Speaker Verification

From Coarse to Fine: Hierarchical Pixel Integration for Lightweight Image Super-Resolution

1 code implementation30 Nov 2022 Jie Liu, Chao Chen, Jie Tang, Gangshan Wu

In the fine area, we use an Intra-Patch Self-Attention (IPSA) module to model long-range pixel dependencies in a local patch, and then a $3\times3$ convolution is applied to process the finest details.

Image Super-Resolution

ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency

1 code implementation29 Nov 2022 Chuming Li, Jie Liu, Yinmin Zhang, Yuhong Wei, Yazhe Niu, Yaodong Yang, Yu Liu, Wanli Ouyang

In the learning phase, each agent minimizes the TD error that is dependent on how the subsequent agents have reacted to their chosen action.

Decision Making Q-Learning +2

Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Report

2 code implementations7 Nov 2022 Andrey Ignatov, Radu Timofte, Maurizio Denna, Abdel Younes, Ganzorig Gankhuyag, Jingang Huh, Myeong Kyun Kim, Kihwan Yoon, Hyeon-Cheol Moon, Seungho Lee, Yoonsik Choe, Jinwoo Jeong, Sungjei Kim, Maciej Smyl, Tomasz Latkowski, Pawel Kubik, Michal Sokolski, Yujie Ma, Jiahao Chao, Zhou Zhou, Hongfan Gao, Zhengfeng Yang, Zhenbing Zeng, Zhengyang Zhuge, Chenghua Li, Dan Zhu, Mengdi Sun, Ran Duan, Yan Gao, Lingshun Kong, Long Sun, Xiang Li, Xingdong Zhang, Jiawei Zhang, Yaqi Wu, Jinshan Pan, Gaocheng Yu, Jin Zhang, Feng Zhang, Zhe Ma, Hongbin Wang, Hojin Cho, Steve Kim, Huaen Li, Yanbo Ma, Ziwei Luo, Youwei Li, Lei Yu, Zhihong Wen, Qi Wu, Haoqiang Fan, Shuaicheng Liu, Lize Zhang, Zhikai Zong, Jeremy Kwon, Junxi Zhang, Mengyuan Li, Nianxiang Fu, Guanchen Ding, Han Zhu, Zhenzhong Chen, Gen Li, Yuanfan Zhang, Lei Sun, Dafeng Zhang, Neo Yang, Fitz Liu, Jerry Zhao, Mustafa Ayazoglu, Bahri Batuhan Bilecen, Shota Hirose, Kasidis Arunruangsirilert, Luo Ao, Ho Chun Leung, Andrew Wei, Jie Liu, Qiang Liu, Dahai Yu, Ao Li, Lei Luo, Ce Zhu, Seongmin Hong, Dongwon Park, Joonhee Lee, Byeong Hyun Lee, Seunggyu Lee, Se Young Chun, Ruiyuan He, Xuhao Jiang, Haihang Ruan, Xinjian Zhang, Jing Liu, Garas Gendy, Nabil Sabor, Jingchao Hou, Guanghui He

While numerous solutions have been proposed for this problem in the past, they are usually not compatible with low-power mobile NPUs having many computational and memory constraints.

Image Super-Resolution

Distinguishable Speaker Anonymization based on Formant and Fundamental Frequency Scaling

no code implementations6 Nov 2022 Jixun Yao, Qing Wang, Yi Lei, Pengcheng Guo, Lei Xie, Namin Wang, Jie Liu

By directly scaling the formant and F0, the speaker distinguishability degradation of the anonymized speech caused by the introduction of other speakers is prevented.

Speaker Verification

Improving the Modality Representation with Multi-View Contrastive Learning for Multimodal Sentiment Analysis

no code implementations28 Oct 2022 Peipei Liu, Xin Zheng, Hong Li, Jie Liu, Yimo Ren, Hongsong Zhu, Limin Sun

At the second stage, a self-supervised contrastive learning is designed for the improvement of the distilled unimodal representations after cross-modal interaction.

Contrastive Learning Multimodal Sentiment Analysis +1

Multi-Granularity Cross-Modality Representation Learning for Named Entity Recognition on Social Media

1 code implementation19 Oct 2022 Peipei Liu, Gaosheng Wang, Hong Li, Jie Liu, Yimo Ren, Hongsong Zhu, Limin Sun

With social media posts tending to be multimodal, Multimodal Named Entity Recognition (MNER) for the text with its accompanying image is attracting more and more attention since some textual components can only be understood in combination with visual information.

named-entity-recognition Named Entity Recognition +3

CEntRE: A paragraph-level Chinese dataset for Relation Extraction among Enterprises

no code implementations19 Oct 2022 Peipei Liu, Hong Li, Zhiyu Wang, Yimo Ren, Jie Liu, Fei Lyu, Hongsong Zhu, Limin Sun

Enterprise relation extraction aims to detect pairs of enterprise entities and identify the business relations between them from unstructured or semi-structured text data, and it is crucial for several real-world applications such as risk analysis, rating research and supply chain security.

Attribute Relation +1

An Improved Structured Mesh Generation Method Based on Physics-informed Neural Networks

no code implementations18 Oct 2022 Xinhai Chen, Jie Liu, Junjun Yan, Zhichao Wang, Chunye Gong

To improve the prediction accuracy of the neural network, we also introduce a novel auxiliary line strategy and an efficient network model during meshing.

Multi-Scale Wavelet Transformer for Face Forgery Detection

no code implementations8 Oct 2022 Jie Liu, Jingjing Wang, Peng Zhang, Chunmao Wang, Di Xie, ShiLiang Pu

To overcome these limitations, we propose a multi-scale wavelet transformer framework for face forgery detection.

Boost CTR Prediction for New Advertisements via Modeling Visual Content

no code implementations23 Sep 2022 Tan Yu, Zhipeng Jin, Jie Liu, Yi Yang, Hongliang Fei, Ping Li

To overcome the limitations of behavior ID features in modeling new ads, we exploit the visual content in ads to boost the performance of CTR prediction models.

Click-Through Rate Prediction Quantization

Multi-features based Semantic Augmentation Networks for Named Entity Recognition in Threat Intelligence

1 code implementation1 Jul 2022 Peipei Liu, Hong Li, Zuoguang Wang, Jie Liu, Yimo Ren, Hongsong Zhu

Extracting cybersecurity entities such as attackers and vulnerabilities from unstructured network texts is an important part of security analysis.

named-entity-recognition Named Entity Recognition +1

MS-RNN: A Flexible Multi-Scale Framework for Spatiotemporal Predictive Learning

1 code implementation7 Jun 2022 Zhifeng Ma, Hao Zhang, Jie Liu

Spatiotemporal predictive learning, which predicts future frames through historical prior knowledge with the aid of deep learning, is widely used in many fields.

Video Prediction

NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results

2 code implementations11 May 2022 Yawei Li, Kai Zhang, Radu Timofte, Luc van Gool, Fangyuan Kong, Mingxi Li, Songwei Liu, Zongcai Du, Ding Liu, Chenhui Zhou, Jingyi Chen, Qingrui Han, Zheyuan Li, Yingqi Liu, Xiangyu Chen, Haoming Cai, Yu Qiao, Chao Dong, Long Sun, Jinshan Pan, Yi Zhu, Zhikai Zong, Xiaoxiao Liu, Zheng Hui, Tao Yang, Peiran Ren, Xuansong Xie, Xian-Sheng Hua, Yanbo Wang, Xiaozhong Ji, Chuming Lin, Donghao Luo, Ying Tai, Chengjie Wang, Zhizhong Zhang, Yuan Xie, Shen Cheng, Ziwei Luo, Lei Yu, Zhihong Wen, Qi Wu1, Youwei Li, Haoqiang Fan, Jian Sun, Shuaicheng Liu, Yuanfei Huang, Meiguang Jin, Hua Huang, Jing Liu, Xinjian Zhang, Yan Wang, Lingshun Long, Gen Li, Yuanfan Zhang, Zuowei Cao, Lei Sun, Panaetov Alexander, Yucong Wang, Minjie Cai, Li Wang, Lu Tian, Zheyuan Wang, Hongbing Ma, Jie Liu, Chao Chen, Yidong Cai, Jie Tang, Gangshan Wu, Weiran Wang, Shirui Huang, Honglei Lu, Huan Liu, Keyan Wang, Jun Chen, Shi Chen, Yuchun Miao, Zimo Huang, Lefei Zhang, Mustafa Ayazoğlu, Wei Xiong, Chengyi Xiong, Fei Wang, Hao Li, Ruimian Wen, Zhijing Yang, Wenbin Zou, Weixin Zheng, Tian Ye, Yuncheng Zhang, Xiangzhen Kong, Aditya Arora, Syed Waqas Zamir, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Dandan Gaoand Dengwen Zhouand Qian Ning, Jingzhu Tang, Han Huang, YuFei Wang, Zhangheng Peng, Haobo Li, Wenxue Guan, Shenghua Gong, Xin Li, Jun Liu, Wanjun Wang, Dengwen Zhou, Kun Zeng, Hanjiang Lin, Xinyu Chen, Jinsheng Fang

The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29. 00dB on DIV2K validation set.

Image Super-Resolution

Dynamic Prototype Convolution Network for Few-Shot Semantic Segmentation

no code implementations CVPR 2022 Jie Liu, Yanqi Bao, Guo-Sen Xie, Huan Xiong, Jan-Jakob Sonke, Efstratios Gavves

Specifically, in DPCN, a dynamic convolution module (DCM) is firstly proposed to generate dynamic kernels from support foreground, then information interaction is achieved by convolution operations over query features using these kernels.

Few-Shot Semantic Segmentation Semantic Segmentation

Fast and Memory-Efficient Network Towards Efficient Image Super-Resolution

1 code implementation18 Apr 2022 Zongcai Du, Ding Liu, Jie Liu, Jie Tang, Gangshan Wu, Lean Fu

Besides, FMEN-S achieves the lowest memory consumption and the second shortest runtime in NTIRE 2022 challenge on efficient super-resolution.

Image Super-Resolution

FedCos: A Scene-adaptive Federated Optimization Enhancement for Performance Improvement

1 code implementation7 Apr 2022 Hao Zhang, Tingting Wu, Siyao Cheng, Jie Liu

On the other hand, it enlarges the distances between local models, resulting in an aggregated global model with poor performance.

Federated Learning

SimT: Handling Open-set Noise for Domain Adaptive Semantic Segmentation

1 code implementation CVPR 2022 Xiaoqing Guo, Jie Liu, Tongliang Liu, Yixuan Yuan

By exploiting computational geometry analysis and properties of segmentation, we design three complementary regularizers, i. e. volume regularization, anchor guidance, convex guarantee, to approximate the true SimT.

Segmentation Semantic Segmentation

Open Set Recognition using Vision Transformer with an Additional Detection Head

1 code implementation16 Mar 2022 Feiyang Cai, Zhenkai Zhang, Jie Liu, Xenofon Koutsoukos

However, in a more realistic open set scenario, traditional classifiers with incomplete knowledge cannot tackle test data that are not from the training classes.

Image Classification Open Set Learning

Privacy protection based on mask template

no code implementations13 Feb 2022 Hao Wang, Yu Bai, Guangmin Sun, Jie Liu

Powerful recognition algorithms are widely used in the Internet or important medical systems, which poses a serious threat to personal privacy.

Cross-domain User Preference Learning for Cold-start Recommendation

no code implementations7 Dec 2021 Huiling Zhou, Jie Liu, Zhikang Li, Jin Yu, Hongxia Yang

With user history represented by a domain-aware sequential model, a frequency encoder is applied to the underlying tags for user content preference learning.

Recommendation Systems

AdaDM: Enabling Normalization for Image Super-Resolution

1 code implementation27 Nov 2021 Jie Liu, Jie Tang, Gangshan Wu

We found that the standard deviation of the residual feature shrinks a lot after normalization layers, which causes the performance degradation in SR networks.

Image Super-Resolution

Auto robust relative radiometric normalization via latent change noise modelling

no code implementations24 Nov 2021 Shiqi Liu, Lu Wang, Jie Lian, Ting Chen, Cong Liu, Xuchen Zhan, Jintao Lu, Jie Liu, Ting Wang, Dong Geng, Hongwei Duan, Yuze Tian

Relative radiometric normalization(RRN) of different satellite images of the same terrain is necessary for change detection, object classification/segmentation, and map-making tasks.

Change Detection

Approaching the Limit of Image Rescaling via Flow Guidance

no code implementations9 Nov 2021 Shang Li, GuiXuan Zhang, Zhengxiong Luo, Jie Liu, Zhi Zeng, Shuwu Zhang

In this paper, instead of directly applying the LR guidance, we propose an additional invertible flow guidance module (FGM), which can transform the downscaled representation to the visually plausible image during downscaling and transform it back during upscaling.

Two-Stage Mesh Deep Learning for Automated Tooth Segmentation and Landmark Localization on 3D Intraoral Scans

no code implementations24 Sep 2021 Tai-Hsien Wu, Chunfeng Lian, Sanghee Lee, Matthew Pastewait, Christian Piers, Jie Liu, Fang Wang, Li Wang, Chiung-Ying Chiu, Wenchi Wang, Christina Jackson, Wei-Lun Chao, Dinggang Shen, Ching-Chang Ko

Our TS-MDL first adopts an end-to-end \emph{i}MeshSegNet method (i. e., a variant of the existing MeshSegNet with both improved accuracy and efficiency) to label each tooth on the downsampled scan.

Code Generation

Edge-Cloud Collaborated Object Detection via Difficult-Case Discriminator

no code implementations29 Aug 2021 Zhiqiang Cao, Zhijun Li, Pan Heng, Yongrui Chen, Daqi Xie, Jie Liu

To address this challenge, we propose a small-big model framework that deploys a big model in the cloud and a small model on the edge devices.

Object object-detection +1

Federated Learning with Dynamic Transformer for Text to Speech

no code implementations9 Jul 2021 Zhenhou Hong, Jianzong Wang, Xiaoyang Qu, Jie Liu, Chendong Zhao, Jing Xiao

Text to speech (TTS) is a crucial task for user interaction, but TTS model training relies on a sizable set of high-quality original datasets.

Federated Learning

From General to Specific: Online Updating for Blind Super-Resolution

no code implementations6 Jul 2021 Shang Li, GuiXuan Zhang, Zhengxiong Luo, Jie Liu, Zhi Zeng, Shuwu Zhang

As a result, most previous methods may suffer a performance drop when the degradations of test images are unknown and various (i. e. the case of blind SR).

Blind Super-Resolution Super-Resolution

Scale-Aware Graph Neural Network for Few-Shot Semantic Segmentation

1 code implementation CVPR 2021 Guo-Sen Xie, Jie Liu, Huan Xiong, Ling Shao

However, they fail to fully leverage the high-order appearance relationships between multi-scale features among the support-query image pairs, thus leading to an inaccurate localization of the query objects.

Few-Shot Semantic Segmentation Semantic Segmentation

Detecting and Correcting IMU Movements During Joint Angle Estimation

no code implementations9 Jun 2021 Chunzhi Yi, Feng Jiang, Baichun Wei, Chifu Yang, Zhen Ding, Jubo Jin, Jie Liu

The results demonstrate our method is a promising solution to detecting and correcting IMU movements during JAE.

Anchor-based Plain Net for Mobile Image Super-Resolution

3 code implementations20 May 2021 Zongcai Du, Jie Liu, Jie Tang, Gangshan Wu

Along with the rapid development of real-world applications, higher requirements on the accuracy and efficiency of image super-resolution (SR) are brought forward.

Image Super-Resolution Quantization

Underwater Target Recognition based on Multi-Decision LOFAR Spectrum Enhancement: A Deep Learning Approach

no code implementations26 Apr 2021 Jie Chen, Jie Liu, Chang Liu, Jian Zhang, Bing Han

To overcome this issue and to further improve the recognition performance, we adopt a deep learning approach for underwater target recognition and propose a LOFAR spectrum enhancement (LSE)-based underwater target recognition scheme, which consists of preprocessing, offline training, and online testing.

LAI Estimation of Cucumber Crop Based on Improved Fully Convolutional Network

no code implementations16 Apr 2021 Weiqi Shu, Ling Wang, Bolong Liu, Jie Liu

How to measure LAI accurately and efficiently is the key to the crop yield estimation problem.

Bidirectional Machine Reading Comprehension for Aspect Sentiment Triplet Extraction

2 code implementations13 Mar 2021 Shaowei Chen, Yu Wang, Jie Liu, Yuelin Wang

Aspect sentiment triplet extraction (ASTE), which aims to identify aspects from review sentences along with their corresponding opinion expressions and sentiments, is an emerging task in fine-grained opinion mining.

Aspect Sentiment Triplet Extraction Machine Reading Comprehension +2

M6: A Chinese Multimodal Pretrainer

no code implementations1 Mar 2021 Junyang Lin, Rui Men, An Yang, Chang Zhou, Ming Ding, Yichang Zhang, Peng Wang, Ang Wang, Le Jiang, Xianyan Jia, Jie Zhang, Jianwei Zhang, Xu Zou, Zhikang Li, Xiaodong Deng, Jie Liu, Jinbao Xue, Huiling Zhou, Jianxin Ma, Jin Yu, Yong Li, Wei Lin, Jingren Zhou, Jie Tang, Hongxia Yang

In this work, we construct the largest dataset for multimodal pretraining in Chinese, which consists of over 1. 9TB images and 292GB texts that cover a wide range of domains.

Image Generation

Truncation-Free Matching System for Display Advertising at Alibaba

no code implementations18 Feb 2021 Jin Li, Jie Liu, Shangzhou Li, Yao Xu, Ran Cao, Qi Li, Biye Jiang, Guan Wang, Han Zhu, Kun Gai, Xiaoqiang Zhu

When receiving a user request, matching system (i) finds the crowds that the user belongs to; (ii) retrieves all ads that have targeted those crowds.

TAG

Few-Shot Semantic Segmentation With Cyclic Memory Network

no code implementations ICCV 2021 Guo-Sen Xie, Huan Xiong, Jie Liu, Yazhou Yao, Ling Shao

Specifically, we first generate N pairs (key and value) of multi-resolution query features guided by the support feature and its mask.

Few-Shot Semantic Segmentation Semantic Segmentation

Colonoscopy Polyp Detection: Domain Adaptation From Medical Report Images to Real-time Videos

no code implementations31 Dec 2020 Zhi-Qin Zhan, Huazhu Fu, Yan-Yao Yang, Jingjing Chen, Jie Liu, Yu-Gang Jiang

However, there are several issues between the image-based training and video-based inference, including domain differences, lack of positive samples, and temporal smoothness.

Domain Adaptation

Inception Convolution with Efficient Dilation Search

1 code implementation CVPR 2021 Jie Liu, Chuming Li, Feng Liang, Chen Lin, Ming Sun, Junjie Yan, Wanli Ouyang, Dong Xu

To develop a practical method for learning complex inception convolution based on the data, a simple but effective search algorithm, referred to as efficient dilation optimization (EDO), is developed.

Human Detection Instance Segmentation +4

The item selection problem for user cold-start recommendation

no code implementations27 Oct 2020 Yitong Meng, Jie Liu, Xiao Yan, James Cheng

When a new user just signs up on a website, we usually have no information about him/her, i. e. no interaction with items, no user profile and no social links with other users.

Recommendation Systems

Adaptive Gradient Method with Resilience and Momentum

no code implementations21 Oct 2020 Jie Liu, Chen Lin, Chuming Li, Lu Sheng, Ming Sun, Junjie Yan, Wanli Ouyang

Several variants of stochastic gradient descent (SGD) have been proposed to improve the learning effectiveness and efficiency when training deep neural networks, among which some recent influential attempts would like to adaptively control the parameter-wise learning rate (e. g., Adam and RMSProp).

Progressive Defense Against Adversarial Attacks for Deep Learning as a Service in Internet of Things

no code implementations15 Oct 2020 Ling Wang, Cheng Zhang, Zejian Luo, ChenGuang Liu, Jie Liu, Xi Zheng, Athanasios Vasilakos

To reduce the computational cost without loss of generality, we present a defense strategy called a progressive defense against adversarial attacks (PDAAA) for efficiently and effectively filtering out the adversarial pixel mutations, which could mislead the neural network towards erroneous outputs, without a-priori knowledge about the attack type.

Residual Feature Distillation Network for Lightweight Image Super-Resolution

2 code implementations24 Sep 2020 Jie Liu, Jie Tang, Gangshan Wu

Thanks to FDC, we can rethink the information multi-distillation network (IMDN) and propose a lightweight and accurate SISR model called residual feature distillation network (RFDN).

Image Super-Resolution

Adaptive Neural Network-Based Approximation to Accelerate Eulerian Fluid Simulation

no code implementations26 Aug 2020 Wenqian Dong, Jie Liu, Zhen Xie, Dong Li

Evaluating with 20, 480 input problems, we show that Smartfluidnet achieves 1. 46x and 590x speedup comparing with a state-of-the-art neural network model and the original fluid simulation respectively on an NVIDIA Titan X Pascal GPU, while providing better simulation quality than the state-of-the-art model.

Poet: Product-oriented Video Captioner for E-commerce

1 code implementation16 Aug 2020 Shengyu Zhang, Ziqi Tan, Jin Yu, Zhou Zhao, Kun Kuang, Jie Liu, Jingren Zhou, Hongxia Yang, Fei Wu

Then, based on the aspects of the video-associated product, we perform knowledge-enhanced spatial-temporal inference on those graphs for capturing the dynamic change of fine-grained product-part characteristics.

Video Captioning

Synchronous Double-channel Recurrent Network for Aspect-Opinion Pair Extraction

1 code implementation ACL 2020 Shaowei Chen, Jie Liu, Yu Wang, Wenzheng Zhang, Ziming Chi

The opinion entity extraction unit and the relation detection unit are developed as two channels to extract opinion entities and relations simultaneously.

Entity Extraction using GAN Opinion Mining +4

Residual Feature Aggregation Network for Image Super-Resolution

no code implementations CVPR 2020 Jie Liu, Wenjie Zhang, Yuting Tang, Jie Tang, Gangshan Wu

To maximize the power of the RFA framework, we further propose an enhanced spatial attention (ESA) block to make the residual features to be more focused on critical spatial contents.

Image Super-Resolution

Deep Convolutional Neural Network-based Bernoulli Heatmap for Head Pose Estimation

no code implementations24 May 2020 Zhongxu Hu, Yang Xing, Chen Lv, Peng Hang, Jie Liu

This paper proposes a novel Bernoulli heatmap for head pose estimation from a single RGB image.

Head Pose Estimation

Stochastic Learning for Sparse Discrete Markov Random Fields with Controlled Gradient Approximation Error

no code implementations12 May 2020 Sinong Geng, Zhaobin Kuang, Jie Liu, Stephen Wright, David Page

We study the $L_1$-regularized maximum likelihood estimator/estimation (MLE) problem for discrete Markov random fields (MRFs), where efficient and scalable learning requires both sparse regularization and approximate inference.

A Comprehensive Survey of Grammar Error Correction

no code implementations2 May 2020 Yu Wang, Yuelin Wang, Jie Liu, Zhuo Liu

More importantly, we discuss four kinds of basic approaches, including statistical machine translation based approach, neural machine translation based approach, classification based approach and language model based approach, six commonly applied performance boosting techniques for GEC systems and two data augmentation methods.

Data Augmentation Language Modelling +3

Computational Performance of a Germline Variant Calling Pipeline for Next Generation Sequencing

no code implementations1 Apr 2020 Jie Liu, Xiaotian Wu, Kai Zhang, Bing Liu, Renyi Bao, Xiao Chen, Yiran Cai, Yiming Shen, Xinjun He, Jun Yan, Weixing Ji

With the booming of next generation sequencing technology and its implementation in clinical practice and life science research, the need for faster and more efficient data analysis methods becomes pressing in the field of sequencing.

InterBERT: Vision-and-Language Interaction for Multi-modal Pretraining

no code implementations30 Mar 2020 Junyang Lin, An Yang, Yichang Zhang, Jie Liu, Jingren Zhou, Hongxia Yang

We pretrain the model with three pretraining tasks, including masked segment modeling (MSM), masked region modeling (MRM) and image-text matching (ITM); and finetune the model on a series of vision-and-language downstream tasks.

Image Retrieval Image-text matching +3

FLAME: A Self-Adaptive Auto-labeling System for Heterogeneous Mobile Processors

no code implementations3 Mar 2020 Jie Liu, Jiawen Liu, Zhen Xie, Dong Li

How to accurately and efficiently label data on a mobile device is critical for the success of training machine learning models on mobile devices.

CTM: Collaborative Temporal Modeling for Action Recognition

no code implementations8 Feb 2020 Qian Liu, Tao Wang, Jie Liu, Yang Guan, Qi Bu, Longfei Yang

In order to learn powerful feature of videos, we propose a Collaborative Temporal Modeling (CTM) block (Figure 1) to learn temporal information for action recognition.

Action Recognition Video Understanding

iqiyi Submission to ActivityNet Challenge 2019 Kinetics-700 challenge: Hierarchical Group-wise Attention

no code implementations7 Feb 2020 Qian Liu, Dongyang Cai, Jie Liu, Nan Ding, Tao Wang

The standard non-local (NL) module is effective in aggregating frame-level features on the task of video classification but presents low parameters efficiency and high computational cost.

General Classification Video Classification

Flow Rate Control in Smart District Heating Systems Using Deep Reinforcement Learning

no code implementations1 Dec 2019 Tinghao Zhang, Jing Luo, Ping Chen, Jie Liu

At high latitudes, many cities adopt a centralized heating system to improve the energy generation efficiency and to reduce pollution.

reinforcement-learning Reinforcement Learning (RL)

Learning to Predict More Accurate Text Instances for Scene Text Detection

no code implementations18 Nov 2019 XiaoQian Li, Jie Liu, Shuwu Zhang, GuiXuan Zhang

At present, multi-oriented text detection methods based on deep neural network have achieved promising performances on various benchmarks.

regression Scene Text Detection +1

Norm-Explicit Quantization: Improving Vector Quantization for Maximum Inner Product Search

2 code implementations12 Nov 2019 Xinyan Dai, Xiao Yan, Kelvin K. W. Ng, Jie Liu, James Cheng

In this paper, we present a new angle to analyze the quantization error, which decomposes the quantization error into norm error and direction error.

Data Compression Quantization

Creating Auxiliary Representations from Charge Definitions for Criminal Charge Prediction

no code implementations12 Nov 2019 Liangyi Kang, Jie Liu, Lingqiao Liu, Qinfeng Shi, Dan Ye

Thus, we propose to create auxiliary fact representations from charge definitions to augment fact descriptions representation.

Sentence

Understanding and Improving Proximity Graph based Maximum Inner Product Search

no code implementations30 Sep 2019 Jie Liu, Xiao Yan, Xinyan Dai, Zhirong Li, James Cheng, Ming-Chang Yang

Then we explain the good performance of ip-NSW as matching the norm bias of the MIPS problem - large norm items have big in-degrees in the ip-NSW proximity graph and a walk on the graph spends the majority of computation on these items, thus effectively avoids unnecessary computation on small norm items.

Single-Path Mobile AutoML: Efficient ConvNet Design and NAS Hyperparameter Optimization

1 code implementation1 Jul 2019 Dimitrios Stamoulis, Ruizhou Ding, Di Wang, Dimitrios Lymberopoulos, Bodhi Priyantha, Jie Liu, Diana Marculescu

In this work, we alleviate the NAS search cost down to less than 3 hours, while achieving state-of-the-art image classification results under mobile latency constraints.

Hyperparameter Optimization Image Classification +1

Performance Analysis and Characterization of Training Deep Learning Models on Mobile Devices

no code implementations10 Jun 2019 Jie Liu, Jiawen Liu, Wan Du, Dong Li

In this paper, we perform a variety of experiments on a representative mobile device (the NVIDIA TX2) to study the performance of training deep learning models.

Single-Path NAS: Device-Aware Efficient ConvNet Design

no code implementations10 May 2019 Dimitrios Stamoulis, Ruizhou Ding, Di Wang, Dimitrios Lymberopoulos, Bodhi Priyantha, Jie Liu, Diana Marculescu

Can we automatically design a Convolutional Network (ConvNet) with the highest image classification accuracy under the latency constraint of a mobile device?

General Classification Image Classification +1

Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours

8 code implementations5 Apr 2019 Dimitrios Stamoulis, Ruizhou Ding, Di Wang, Dimitrios Lymberopoulos, Bodhi Priyantha, Jie Liu, Diana Marculescu

Can we automatically design a Convolutional Network (ConvNet) with the highest image classification accuracy under the runtime constraint of a mobile device?

General Classification Image Classification +1

Rotated Feature Network for multi-orientation object detection

no code implementations23 Mar 2019 Zhixin Zhang, Xudong Chen, Jie Liu, Kaibo Zhou

General detectors follow the pipeline that feature maps extracted from ConvNets are shared between classification and regression tasks.

Classification General Classification +5

Tencent ML-Images: A Large-Scale Multi-Label Image Database for Visual Representation Learning

1 code implementation7 Jan 2019 Baoyuan Wu, Weidong Chen, Yanbo Fan, Yong Zhang, Jinlong Hou, Jie Liu, Tong Zhang

In this work, we propose to train CNNs from images annotated with multiple tags, to enhance the quality of visual representation of the trained CNN model.

Image Classification object-detection +5

Norm-Range Partition: A Universal Catalyst for LSH based Maximum Inner Product Search (MIPS)

1 code implementation22 Oct 2018 Xiao Yan, Xinyan Dai, Jie Liu, Kaiwen Zhou, James Cheng

Recently, locality sensitive hashing (LSH) was shown to be effective for MIPS and several algorithms including $L_2$-ALSH, Sign-ALSH and Simple-LSH have been proposed.

On the Acceleration of L-BFGS with Second-Order Information and Stochastic Batches

no code implementations14 Jul 2018 Jie Liu, Yu Rong, Martin Takac, Junzhou Huang

This paper proposes a framework of L-BFGS based on the (approximate) second-order information with stochastic batches, as a novel approach to the finite-sum minimization problems.

A Spatial and Temporal Features Mixture Model with Body Parts for Video-based Person Re-Identification

no code implementations3 Jul 2018 Jie Liu, Cheng Sun, Xiang Xu, Baomin Xu, Shuangyuan Yu

In this paper we propose a novel Spatial and Temporal Features Mixture Model (STFMM) based on convolutional neural network (CNN) and recurrent neural network (RNN), in which the human body is split into $N$ parts in horizontal direction so that we can obtain more specific features.

Video-Based Person Re-Identification

Question Answering over Freebase via Attentive RNN with Similarity Matrix based CNN

no code implementations10 Apr 2018 Yingqi Qu, Jie Liu, Liangyi Kang, Qinfeng Shi, Dan Ye

To preserve more original information, we propose an attentive recurrent neural network with similarity matrix based convolutional neural network (AR-SMCNN) model, which is able to capture comprehensive hierarchical information utilizing the advantages of both RNN and CNN.

Question Answering

MLE-induced Likelihood for Markov Random Fields

no code implementations27 Mar 2018 Jie Liu, Hao Zheng

Especially as the size of the MRF increases, both the numerical performance and the computational cost of our approach remain consistently satisfactory, whereas Laplace approximation deteriorates and pseudolikelihood becomes computationally unbearable.

Stochastic Recursive Gradient Algorithm for Nonconvex Optimization

no code implementations20 May 2017 Lam M. Nguyen, Jie Liu, Katya Scheinberg, Martin Takáč

In this paper, we study and analyze the mini-batch version of StochAstic Recursive grAdient algoritHm (SARAH), a method employing the stochastic recursive gradient, for solving empirical loss minimization for the case of nonconvex losses.

SARAH: A Novel Method for Machine Learning Problems Using Stochastic Recursive Gradient

no code implementations ICML 2017 Lam M. Nguyen, Jie Liu, Katya Scheinberg, Martin Takáč

In this paper, we propose a StochAstic Recursive grAdient algoritHm (SARAH), as well as its practical variant SARAH+, as a novel approach to the finite-sum minimization problems.

BIG-bench Machine Learning

Projected Semi-Stochastic Gradient Descent Method with Mini-Batch Scheme under Weak Strong Convexity Assumption

no code implementations16 Dec 2016 Jie Liu, Martin Takac

We propose a projected semi-stochastic gradient descent method with mini-batch for improving both the theoretical complexity and practical performance of the general stochastic gradient descent method (SGD).

BIG-bench Machine Learning

Topic Aware Neural Response Generation

1 code implementation21 Jun 2016 Chen Xing, Wei Wu, Yu Wu, Jie Liu, YaLou Huang, Ming Zhou, Wei-Ying Ma

We consider incorporating topic information into the sequence-to-sequence framework to generate informative and interesting responses for chatbots.

Response Generation

Mini-Batch Semi-Stochastic Gradient Descent in the Proximal Setting

no code implementations16 Apr 2015 Jakub Konečný, Jie Liu, Peter Richtárik, Martin Takáč

Our method first performs a deterministic step (computation of the gradient of the objective function at the starting point), followed by a large number of stochastic steps.

mS2GD: Mini-Batch Semi-Stochastic Gradient Descent in the Proximal Setting

no code implementations17 Oct 2014 Jakub Konečný, Jie Liu, Peter Richtárik, Martin Takáč

Our method first performs a deterministic step (computation of the gradient of the objective function at the starting point), followed by a large number of stochastic steps.

Defuzzify firstly or finally: Dose it matter in fuzzy DEMATEL under uncertain environment?

no code implementations20 Mar 2014 Yunpeng Li, Ya Li, Jie Liu, Yong Deng

The results of defuzzification at the first step are not coincide with the results of defuzzification at the final step. It seems that the alternative is to defuzzification in the final step in fuzzy DEMATEL.

Decision Making

Bayesian Estimation of Latently-grouped Parameters in Undirected Graphical Models

no code implementations NeurIPS 2013 Jie Liu, David Page

In large-scale applications of undirected graphical models, such as social networks and biological networks, similar patterns occur frequently and give rise to similar parameters.

A brief network analysis of Artificial Intelligence publication

no code implementations23 Nov 2013 Yunpeng Li, Jie Liu, Yong Deng

In this paper, we present an illustration to the history of Artificial Intelligence(AI) with a statistical analysis of publish since 1940.

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