Search Results for author: Li Chen

Found 180 papers, 61 papers with code

FontStudio: Shape-Adaptive Diffusion Model for Coherent and Consistent Font Effect Generation

no code implementations12 Jun 2024 Xinzhi Mu, Li Chen, Bohan Chen, Shuyang Gu, Jianmin Bao, Dong Chen, Ji Li, Yuhui Yuan

This task essentially requires generating coherent and consistent visual content within the confines of a font-shaped canvas, as opposed to a traditional rectangular canvas.

Text-to-Image Generation

Fairness-Aware Meta-Learning via Nash Bargaining

no code implementations11 Jun 2024 Yi Zeng, Xuelin Yang, Li Chen, Cristian Canton Ferrer, Ming Jin, Michael I. Jordan, Ruoxi Jia

To address issues of group-level fairness in machine learning, it is natural to adjust model parameters based on specific fairness objectives over a sensitive-attributed validation set.

Fairness Image Classification +2

Matryoshka Representation Learning for Recommendation

1 code implementation11 Jun 2024 Riwei Lai, Li Chen, Weixin Chen, Rui Chen

In this paper, we introduce a novel matryoshka representation learning method for recommendation (MRL4Rec), by which we restructure user and item vectors into matryoshka representations with incrementally dimensional and overlapping vector spaces to explicitly represent user preferences and item features at different hierarchical levels.

Recommendation Systems Representation Learning

Learning Manipulation by Predicting Interaction

1 code implementation1 Jun 2024 Jia Zeng, Qingwen Bu, Bangjun Wang, Wenke Xia, Li Chen, Hao Dong, Haoming Song, Dong Wang, Di Hu, Ping Luo, Heming Cui, Bin Zhao, Xuelong Li, Yu Qiao, Hongyang Li

To this end, we propose a general pre-training pipeline that learns Manipulation by Predicting the Interaction (MPI) and enhances the visual representation. Given a pair of keyframes representing the initial and final states, along with language instructions, our algorithm predicts the transition frame and detects the interaction object, respectively.

Representation Learning

Navigating User Experience of ChatGPT-based Conversational Recommender Systems: The Effects of Prompt Guidance and Recommendation Domain

no code implementations22 May 2024 Yizhe Zhang, Yucheng Jin, Li Chen, Ting Yang

Therefore, we have developed a ChatGPT-based CRS to investigate the impact of these two factors, prompt guidance (PG) and recommendation domain (RD), on the overall user experience of the system.

Recommendation Systems

Q2A: Querying Implicit Fully Continuous Feature Pyramid to Align Features for Medical Image Segmentation

no code implementations15 Apr 2024 Jiahao Yu, Li Chen

Therefore, we propose Q2A, a novel one-step query-based aligning paradigm, to solve the feature misalignment problem in the INR-based decoder.

Decoder Image Segmentation +2

Enhancing Programming Education with ChatGPT: A Case Study on Student Perceptions and Interactions in a Python Course

no code implementations20 Mar 2024 Boxaun Ma, Li Chen, Shin'ichi Konomi

The integration of ChatGPT as a supportive tool in education, notably in programming courses, addresses the unique challenges of programming education by providing assistance with debugging, code generation, and explanations.

Code Generation

FedClust: Optimizing Federated Learning on Non-IID Data through Weight-Driven Client Clustering

no code implementations7 Mar 2024 Md Sirajul Islam, Simin Javaherian, Fei Xu, Xu Yuan, Li Chen, Nian-Feng Tzeng

Clustered federated learning (CFL) addresses this challenge by grouping clients based on the similarity of their data distributions.

Federated Learning

Exploring the Design of Generative AI in Supporting Music-based Reminiscence for Older Adults

no code implementations3 Mar 2024 Yucheng Jin, Wanling Cai, Li Chen, Yizhe Zhang, Gavin Doherty, Tonglin Jiang

Music-based reminiscence has the potential to positively impact the psychological well-being of older adults.

T-HITL Effectively Addresses Problematic Associations in Image Generation and Maintains Overall Visual Quality

no code implementations27 Feb 2024 Susan Epstein, Li Chen, Alessandro Vecchiato, Ankit Jain

Building on sociological literature (Blumer, 1958) and mapping representations to model behaviors, we have developed a taxonomy to study problematic associations in image generation models.

Image Generation

FedFair^3: Unlocking Threefold Fairness in Federated Learning

no code implementations29 Jan 2024 Simin Javaherian, Sanjeev Panta, Shelby Williams, Md Sirajul Islam, Li Chen

In addition to having a fair client-selection strategy, we enforce an equitable number of rounds for client participation and ensure a fair accuracy distribution over the clients.

Fairness Federated Learning

Adaptive Hardness Negative Sampling for Collaborative Filtering

1 code implementation10 Jan 2024 Riwei Lai, Rui Chen, Qilong Han, Chi Zhang, Li Chen

Negative sampling is essential for implicit collaborative filtering to provide proper negative training signals so as to achieve desirable performance.

Collaborative Filtering

Joint Channel Estimation and Data Recovery for Millimeter Massive MIMO: Using Pilot to Capture Principal Components

no code implementations3 Jan 2024 Shusen Cai, Li Chen, Yunfei Chen, Huarui Yin, Weidong Wang

In Stage 1, differing from the traditional PF-based methods, the proposed PF-assisted method is utilized to capture the angle of arrival (AoA) of principal components (PC) of channels.

Named Entity Driven Zero-Shot Image Manipulation

no code implementations CVPR 2024 Zhida Feng, Li Chen, Jing Tian, Jiaxiang Liu, Shikun Feng

We introduced StyleEntity a zero-shot image manipulation model that utilizes named entities as proxies during its training phase.

Image Manipulation

Visual Point Cloud Forecasting enables Scalable Autonomous Driving

1 code implementation CVPR 2024 Zetong Yang, Li Chen, Yanan sun, Hongyang Li

To resolve this, we bring up a new pre-training task termed as visual point cloud forecasting - predicting future point clouds from historical visual input.

Motion Forecasting

LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Driving

1 code implementation26 Dec 2023 Tianyu Li, Peijin Jia, Bangjun Wang, Li Chen, Kun Jiang, Junchi Yan, Hongyang Li

A map, as crucial information for downstream applications of an autonomous driving system, is usually represented in lanelines or centerlines.

Autonomous Driving

Wideband Sample Rate Converter Using Cascaded Parallel-serial Structure for Synthetic Instrumentation

no code implementations22 Dec 2023 Ruiyuan Ming, Peng Ye, Kuojun Yang, Zhixiang Pan, Li Chen, Xuetao Liu

In the meantime, the decimation factor of the CIC filter can be adjusted flexibly in a wide range, which is used to improve the system configuration flexibility.

DriveLM: Driving with Graph Visual Question Answering

1 code implementation21 Dec 2023 Chonghao Sima, Katrin Renz, Kashyap Chitta, Li Chen, Hanxue Zhang, Chengen Xie, Ping Luo, Andreas Geiger, Hongyang Li

The experiments demonstrate that Graph VQA provides a simple, principled framework for reasoning about a driving scene, and DriveLM-Data provides a challenging benchmark for this task.

Autonomous Driving Question Answering +1

Optimal coordination in Minority Game: A solution from reinforcement learning

no code implementations20 Dec 2023 Guozhong Zheng, Weiran Cai, Guanxiao Qi, Jiqiang Zhang, Li Chen

We reveal that the population is able to reach the optimal allocation when individuals appreciate both the past experience and rewards in the future, and they are able to balance the exploitation of their Q-tables and the exploration by randomly acting.

Q-Learning reinforcement-learning

Opara: Exploiting Operator Parallelism for Expediting DNN Inference on GPUs

1 code implementation16 Dec 2023 Aodong Chen, Fei Xu, Li Han, Yuan Dong, Li Chen, Zhi Zhou, Fangming Liu

GPUs have become the \emph{defacto} hardware devices for accelerating Deep Neural Network (DNN) inference workloads.

Scheduling

Open-sourced Data Ecosystem in Autonomous Driving: the Present and Future

2 code implementations6 Dec 2023 Hongyang Li, Yang Li, Huijie Wang, Jia Zeng, Huilin Xu, Pinlong Cai, Li Chen, Junchi Yan, Feng Xu, Lu Xiong, Jingdong Wang, Futang Zhu, Chunjing Xu, Tiancai Wang, Fei Xia, Beipeng Mu, Zhihui Peng, Dahua Lin, Yu Qiao

With the continuous maturation and application of autonomous driving technology, a systematic examination of open-source autonomous driving datasets becomes instrumental in fostering the robust evolution of the industry ecosystem.

Autonomous Driving

Audio-visual Saliency for Omnidirectional Videos

no code implementations9 Nov 2023 Yuxin Zhu, Xilei Zhu, Huiyu Duan, Jie Li, Kaiwei Zhang, Yucheng Zhu, Li Chen, Xiongkuo Min, Guangtao Zhai

Visual saliency prediction for omnidirectional videos (ODVs) has shown great significance and necessity for omnidirectional videos to help ODV coding, ODV transmission, ODV rendering, etc..

Saliency Prediction

FMMRec: Fairness-aware Multimodal Recommendation

no code implementations26 Oct 2023 Weixin Chen, Li Chen, Yongxin Ni, Yuhan Zhao, Fajie Yuan, Yongfeng Zhang

Recently, multimodal recommendations have gained increasing attention for effectively addressing the data sparsity problem by incorporating modality-based representations.

Attribute counterfactual +3

LanguageMPC: Large Language Models as Decision Makers for Autonomous Driving

no code implementations4 Oct 2023 Hao Sha, Yao Mu, YuXuan Jiang, Li Chen, Chenfeng Xu, Ping Luo, Shengbo Eben Li, Masayoshi Tomizuka, Wei Zhan, Mingyu Ding

Existing learning-based autonomous driving (AD) systems face challenges in comprehending high-level information, generalizing to rare events, and providing interpretability.

Autonomous Driving Decision Making

MindShift: Leveraging Large Language Models for Mental-States-Based Problematic Smartphone Use Intervention

no code implementations28 Sep 2023 Ruolan Wu, Chun Yu, Xiaole Pan, Yujia Liu, Ningning Zhang, Yue Fu, YuHan Wang, Zhi Zheng, Li Chen, Qiaolei Jiang, Xuhai Xu, Yuanchun Shi

We first conducted a Wizard-of-Oz study (N=12) and an interview study (N=10) to summarize the mental states behind problematic smartphone use: boredom, stress, and inertia.

Persuasion Strategies

Decoding trust: A reinforcement learning perspective

no code implementations26 Sep 2023 Guozhong Zheng, Jiqiang Zhang, Jing Zhang, Weiran Cai, Li Chen

In the pairwise scenario, we reveal that high levels of trust and trustworthiness emerge when individuals appreciate both their historical experience and returns in the future.

Decision Making Q-Learning +1

Decision Fusion Network with Perception Fine-tuning for Defect Classification

no code implementations22 Sep 2023 Xiaoheng Jiang, Shilong Tian, Zhiwen Zhu, Yang Lu, Hao liu, Li Chen, Shupan Li, Mingliang Xu

In addition, we propose a perception fine-tuning module (PFM) that fine-tunes the foreground and background during the segmentation stage.

SCVCNet: Sliding cross-vector convolution network for cross-task and inter-individual-set EEG-based cognitive workload recognition

1 code implementation21 Sep 2023 Qi Wang, Li Chen, Zhiyuan Zhan, Jianhua Zhang, Zhong Yin

This paper presents a generic approach for applying the cognitive workload recognizer by exploiting common electroencephalogram (EEG) patterns across different human-machine tasks and individual sets.

EEG

MMST-ViT: Climate Change-aware Crop Yield Prediction via Multi-Modal Spatial-Temporal Vision Transformer

1 code implementation ICCV 2023 Fudong Lin, Summer Crawford, Kaleb Guillot, Yihe Zhang, Yan Chen, Xu Yuan, Li Chen, Shelby Williams, Robert Minvielle, Xiangming Xiao, Drew Gholson, Nicolas Ashwell, Tri Setiyono, Brenda Tubana, Lu Peng, Magdy Bayoumi, Nian-Feng Tzeng

In this work, we develop a deep learning-based solution, namely Multi-Modal Spatial-Temporal Vision Transformer (MMST-ViT), for predicting crop yields at the county level across the United States, by considering the effects of short-term meteorological variations during the growing season and the long-term climate change on crops.

Contrastive Learning Crop Yield Prediction +1

PhotoVerse: Tuning-Free Image Customization with Text-to-Image Diffusion Models

1 code implementation11 Sep 2023 Li Chen, Mengyi Zhao, Yiheng Liu, Mingxu Ding, Yangyang Song, Shizun Wang, Xu Wang, Hao Yang, Jing Liu, Kang Du, Min Zheng

Personalized text-to-image generation has emerged as a powerful and sought-after tool, empowering users to create customized images based on their specific concepts and prompts.

Text-to-Image Generation

Large Language Models for Generative Recommendation: A Survey and Visionary Discussions

no code implementations3 Sep 2023 Lei LI, Yongfeng Zhang, Dugang Liu, Li Chen

Large language models (LLM) not only have revolutionized the field of natural language processing (NLP) but also have the potential to reshape many other fields, e. g., recommender systems (RS).

Recommendation Systems Re-Ranking

Dynamic landslide susceptibility mapping over recent three decades to uncover variations in landslide causes in subtropical urban mountainous areas

1 code implementation23 Aug 2023 Peifeng Ma, Li Chen, Chang Yu, Qing Zhu, Yulin Ding

The chosen study area is Lantau Island, Hong Kong, where we conducted a comprehensive dynamic LSA spanning from 1992 to 2019.

Augmented Negative Sampling for Collaborative Filtering

1 code implementation11 Aug 2023 Yuhan Zhao, Rui Chen, Riwei Lai, Qilong Han, Hongtao Song, Li Chen

To balance efficiency and effectiveness, the vast majority of existing methods follow the two-pass approach, in which the first pass samples a fixed number of unobserved items by a simple static distribution and then the second pass selects the final negative items using a more sophisticated negative sampling strategy.

Collaborative Filtering

AvatarVerse: High-quality & Stable 3D Avatar Creation from Text and Pose

1 code implementation7 Aug 2023 Huichao Zhang, Bowen Chen, Hao Yang, Liao Qu, Xu Wang, Li Chen, Chao Long, Feida Zhu, Kang Du, Min Zheng

We present AvatarVerse, a stable pipeline for generating expressive high-quality 3D avatars from nothing but text descriptions and pose guidance.

Text-to-3D-Human Generation

DriveAdapter: Breaking the Coupling Barrier of Perception and Planning in End-to-End Autonomous Driving

1 code implementation ICCV 2023 Xiaosong Jia, Yulu Gao, Li Chen, Junchi Yan, Patrick Langechuan Liu, Hongyang Li

We find that even equipped with a SOTA perception model, directly letting the student model learn the required inputs of the teacher model leads to poor driving performance, which comes from the large distribution gap between predicted privileged inputs and the ground-truth.

Autonomous Driving CARLA longest6

Perceptual Quality Assessment of Omnidirectional Audio-visual Signals

1 code implementation20 Jul 2023 Xilei Zhu, Huiyu Duan, Yuqin Cao, Yuxin Zhu, Yucheng Zhu, Jing Liu, Li Chen, Xiongkuo Min, Guangtao Zhai

Omnidirectional videos (ODVs) play an increasingly important role in the application fields of medical, education, advertising, tourism, etc.

End-to-end Autonomous Driving: Challenges and Frontiers

1 code implementation29 Jun 2023 Li Chen, Penghao Wu, Kashyap Chitta, Bernhard Jaeger, Andreas Geiger, Hongyang Li

The autonomous driving community has witnessed a rapid growth in approaches that embrace an end-to-end algorithm framework, utilizing raw sensor input to generate vehicle motion plans, instead of concentrating on individual tasks such as detection and motion prediction.

Autonomous Driving motion prediction

Near-Field Beam Management for Extremely Large-Scale Array Communications

no code implementations28 Jun 2023 Changsheng You, Yunpu Zhang, Chenyu Wu, Yong Zeng, Beixiong Zheng, Li Chen, Linglong Dai, A. Lee Swindlehurst

Extremely large-scale arrays (XL-arrays) have emerged as a promising technology to achieve super-high spectral efficiency and spatial resolution in future wireless systems.

Management Scheduling

ParamNet: A Parameter-variable Network for Fast Stain Normalization

1 code implementation11 May 2023 Hongtao Kang, Die Luo, Li Chen, Junbo Hu, Shenghua Cheng, Tingwei Quan, Shaoqun Zeng, Xiuli Liu

The feature of parameter variable ensures that our network has a sufficient capability for various stain normalization tasks.

Computational Efficiency Parameter Prediction

Strategic Responses to Personalized Pricing and Demand for Privacy: An Experiment

no code implementations22 Apr 2023 Inácio Bó, Li Chen, Rustamdjan Hakimov

We consider situations where consumers are aware that a statistical model determines the price of a product based on their observed behavior.

Two-step Band-split Neural Network Approach for Full-band Residual Echo Suppression

no code implementations13 Mar 2023 Zihan Zhang, Shimin Zhang, Mingshuai Liu, Yanhong Leng, Zhe Han, Li Chen, Lei Xie

This paper describes a Two-step Band-split Neural Network (TBNN) approach for full-band acoustic echo cancellation.

Acoustic echo cancellation

Personalized speech enhancement combining band-split RNN and speaker attentive module

no code implementations20 Feb 2023 Xiaohuai Le, Li Chen, Chao He, Yiqing Guo, Cheng Chen, Xianjun Xia, Jing Lu

Target speaker information can be utilized in speech enhancement (SE) models to more effectively extract the desired speech.

Speech Enhancement

SwiftAvatar: Efficient Auto-Creation of Parameterized Stylized Character on Arbitrary Avatar Engines

no code implementations19 Jan 2023 Shizun Wang, Weihong Zeng, Xu Wang, Hao Yang, Li Chen, Yi Yuan, Yunzhao Zeng, Min Zheng, Chuang Zhang, Ming Wu

To this end, we propose SwiftAvatar, a novel avatar auto-creation framework that is evidently superior to previous works.

Mixed Near- and Far-Field Communications for Extremely Large-Scale Array: An Interference Perspective

no code implementations18 Jan 2023 Yunpu Zhang, Changsheng You, Li Chen, Beixiong Zheng

For this scenario, we first obtain a closed-form expression for the inter-user interference at the near-field user caused by the far-field beam by using Fresnel functions, based on which the effects of the number of BS antennas, far-field user (FU) angle, near-field user (NU) angle and distance are analyzed.

Policy Pre-training for Autonomous Driving via Self-supervised Geometric Modeling

1 code implementation3 Jan 2023 Penghao Wu, Li Chen, Hongyang Li, Xiaosong Jia, Junchi Yan, Yu Qiao

Witnessing the impressive achievements of pre-training techniques on large-scale data in the field of computer vision and natural language processing, we wonder whether this idea could be adapted in a grab-and-go spirit, and mitigate the sample inefficiency problem for visuomotor driving.

Autonomous Driving Decision Making

Distilling Focal Knowledge From Imperfect Expert for 3D Object Detection

no code implementations CVPR 2023 Jia Zeng, Li Chen, Hanming Deng, Lewei Lu, Junchi Yan, Yu Qiao, Hongyang Li

Specifically, a set of queries are leveraged to locate the instance-level areas for masked feature generation, to intensify feature representation ability in these areas.

3D Object Detection Knowledge Distillation +2

Local and Global Logit Adjustments for Long-Tailed Learning

no code implementations ICCV 2023 Yingfan Tao, Jingna Sun, Hao Yang, Li Chen, Xu Wang, Wenming Yang, Daniel Du, Min Zheng

LGLA consists of two core components: a Class-aware Logit Adjustment (CLA) strategy and an Adaptive Angular Weighted (AAW) loss.

Planning-oriented Autonomous Driving

2 code implementations CVPR 2023 Yihan Hu, Jiazhi Yang, Li Chen, Keyu Li, Chonghao Sima, Xizhou Zhu, Siqi Chai, Senyao Du, Tianwei Lin, Wenhai Wang, Lewei Lu, Xiaosong Jia, Qiang Liu, Jifeng Dai, Yu Qiao, Hongyang Li

Oriented at this, we revisit the key components within perception and prediction, and prioritize the tasks such that all these tasks contribute to planning.

Autonomous Driving Philosophy

You Only Need a Good Embeddings Extractor to Fix Spurious Correlations

no code implementations12 Dec 2022 Raghav Mehta, Vítor Albiero, Li Chen, Ivan Evtimov, Tamar Glaser, Zhiheng Li, Tal Hassner

With experiments on a wide range of pre-trained models and pre-training datasets, we show that the capacity of the pre-training model and the size of the pre-training dataset matters.

Respecting priorities versus respecting preferences in school choice: When is there a trade-off?

no code implementations6 Dec 2022 Estelle Cantillon, Li Chen, Juan S. Pereyra

A classic trade-off that school districts face when deciding which matching algorithm to use is that it is not possible to always respect both priorities and preferences.

Learning-Augmented B-Trees

no code implementations16 Nov 2022 Xinyuan Cao, Jingbang Chen, Li Chen, Chris Lambert, Richard Peng, Daniel Sleator

We study learning-augmented binary search trees (BSTs) and B-Trees via Treaps with composite priorities.

Deep Learning is Provably Robust to Symmetric Label Noise

no code implementations26 Oct 2022 Carey E. Priebe, Ningyuan Huang, Soledad Villar, Cong Mu, Li Chen

We conjecture that for general label noise, mitigation strategies that make use of the noisy data will outperform those that ignore the noisy data.

Memorization

Oscillatory cooperation prevalence emerges from misperception

no code implementations17 Oct 2022 Jing Zhang, Zhao Li, Jiqiang Zhang, Lin Ma, Guozhong Zheng, Li Chen

Here we show that oscillatory behaviors naturally emerge if incomplete information is incorporated into the cooperation evolution of a non-Markov model.

Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe

2 code implementations12 Sep 2022 Hongyang Li, Chonghao Sima, Jifeng Dai, Wenhai Wang, Lewei Lu, Huijie Wang, Jia Zeng, Zhiqi Li, Jiazhi Yang, Hanming Deng, Hao Tian, Enze Xie, Jiangwei Xie, Li Chen, Tianyu Li, Yang Li, Yulu Gao, Xiaosong Jia, Si Liu, Jianping Shi, Dahua Lin, Yu Qiao

As sensor configurations get more complex, integrating multi-source information from different sensors and representing features in a unified view come of vital importance.

Autonomous Driving

Time-constrained Dynamic Mechanisms for College Admissions

no code implementations25 Jul 2022 Li Chen, Juan S. Pereyra, Min Zhu

Recent literature shows that dynamic matching mechanisms may outperform the standard mechanisms to deliver desirable results.

Robust Landmark-based Stent Tracking in X-ray Fluoroscopy

no code implementations20 Jul 2022 Luojie Huang, Yikang Liu, Li Chen, Eric Z. Chen, Xiao Chen, Shanhui Sun

Even though angioplasty devices are designed to have radiopaque markers for the ease of tracking, current methods struggle to deliver satisfactory results due to the small marker size and complex scenes in angioplasty.

ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning

1 code implementation15 Jul 2022 Shengchao Hu, Li Chen, Penghao Wu, Hongyang Li, Junchi Yan, DaCheng Tao

In particular, we propose a spatial-temporal feature learning scheme towards a set of more representative features for perception, prediction and planning tasks simultaneously, which is called ST-P3.

Ranked #7 on Bird's-Eye View Semantic Segmentation on nuScenes (IoU ped - 224x480 - Vis filter. - 100x100 at 0.5 metric)

Autonomous Driving Bird's-Eye View Semantic Segmentation +1

Cramér-Rao Bounds of Near-Field Positioning Based on Electromagnetic Propagation Model

no code implementations2 Jul 2022 Ang Chen, Li Chen, Yunfei Chen, Changsheng You, Guo Wei, F. Richard Yu

In this paper, we improve the near-field positioning technology from the classical spherical wavefront model (SWM) to the more accurate and true electromagnetic propagation model (EPM).

Enhanced Deep Animation Video Interpolation

2 code implementations25 Jun 2022 Wang Shen, Cheng Ming, Wenbo Bao, Guangtao Zhai, Li Chen, Zhiyong Gao

With AutoFI and SktFI, the interpolated animation frames show high perceptual quality.

Level 2 Autonomous Driving on a Single Device: Diving into the Devils of Openpilot

no code implementations16 Jun 2022 Li Chen, Tutian Tang, Zhitian Cai, Yang Li, Penghao Wu, Hongyang Li, Jianping Shi, Junchi Yan, Yu Qiao

Equipped with a wide span of sensors, predominant autonomous driving solutions are becoming more modular-oriented for safe system design.

Autonomous Driving

Deep Learning with Label Noise: A Hierarchical Approach

no code implementations28 May 2022 Li Chen, Ningyuan Huang, Cong Mu, Hayden S. Helm, Kate Lytvynets, Weiwei Yang, Carey E. Priebe

Our hierarchical approach improves upon regular deep neural networks in learning with label noise.

Meta-Learning

HDGT: Heterogeneous Driving Graph Transformer for Multi-Agent Trajectory Prediction via Scene Encoding

1 code implementation30 Apr 2022 Xiaosong Jia, Penghao Wu, Li Chen, Yu Liu, Hongyang Li, Junchi Yan

Based on these observations, we propose Heterogeneous Driving Graph Transformer (HDGT), a backbone modelling the driving scene as a heterogeneous graph with different types of nodes and edges.

Autonomous Driving graph construction +3

Hierarchical-Absolute Reciprocity Calibration for Millimeter-wave Hybrid Beamforming Systems

no code implementations14 Apr 2022 Li Chen, Rongjiang Nie, Yunfei Chen, Weidong Wang

The results reveal that the estimation errors of mismatch coefficients of digital and analog chains are uncorrelated, and that the mismatch coefficients of receive digital chains can be estimated perfectly.

ERNIE-SPARSE: Learning Hierarchical Efficient Transformer Through Regularized Self-Attention

no code implementations23 Mar 2022 Yang Liu, Jiaxiang Liu, Li Chen, Yuxiang Lu, Shikun Feng, Zhida Feng, Yu Sun, Hao Tian, Hua Wu, Haifeng Wang

We argue that two factors, information bottleneck sensitivity and inconsistency between different attention topologies, could affect the performance of the Sparse Transformer.

Sparse Learning text-classification +1

PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark

2 code implementations21 Mar 2022 Li Chen, Chonghao Sima, Yang Li, Zehan Zheng, Jiajie Xu, Xiangwei Geng, Hongyang Li, Conghui He, Jianping Shi, Yu Qiao, Junchi Yan

Methods for 3D lane detection have been recently proposed to address the issue of inaccurate lane layouts in many autonomous driving scenarios (uphill/downhill, bump, etc.).

3D Lane Detection Autonomous Driving +1

Conversational Recommendation: A Grand AI Challenge

no code implementations17 Mar 2022 Dietmar Jannach, Li Chen

Animated avatars, which look and talk like humans, are iconic visions of the future of AI-powered systems.

Recommendation Systems

A Survey of Surface Defect Detection of Industrial Products Based on A Small Number of Labeled Data

no code implementations11 Mar 2022 Qifan Jin, Li Chen

Therefore, this paper reviews the methods of surface defect detection of industrial products based on a small number of labeled data, and this method is divided into traditional image processing-based industrial product surface defect detection methods and deep learning-based industrial product surface defect detection methods suitable for a small number of labeled data.

Data Augmentation Defect Detection +1

Personalized Prompt Learning for Explainable Recommendation

1 code implementation15 Feb 2022 Lei LI, Yongfeng Zhang, Li Chen

In the latter case, ID vectors are randomly initialized but the model is trained in advance on large corpora, so they are actually in different learning stages.

Explainable Recommendation Recommendation Systems +1

Probabilistic fair behaviors spark its boost in the Ultimatum Game: the strength of good Samaritans

no code implementations12 Feb 2022 Guozhong Zheng, Jiqiang Zhang, Rizhou Liang, Lin Ma, Li Chen

Behavioral experiments on the Ultimatum Game have shown that we human beings have remarkable preference in fair play, contradicting the predictions by the game theory.

Fairness

A Coding Framework and Benchmark towards Compressed Video Understanding

no code implementations6 Feb 2022 Yuan Tian, Guo Lu, Yichao Yan, Guangtao Zhai, Li Chen, Zhiyong Gao

However, in real-world scenarios, the videos are first compressed before the transportation and then decompressed for understanding.

Video Understanding

SoftCollage: A Differentiable Probabilistic Tree Generator for Image Collage

1 code implementation CVPR 2022 Jiahao Yu, Li Chen, Mingrui Zhang, Mading Li

While several recent works exploit tree-based algorithm to preserve image content better, all of them resort to hand-crafted adjustment rules to optimize the collage tree structure, leading to the failure of fully exploring the structure space of collage tree.

Finding Optimal Tangent Points for Reducing Distortions of Hard-label Attacks

1 code implementation NeurIPS 2021 Chen Ma, Xiangyu Guo, Li Chen, Jun-Hai Yong, Yisen Wang

In this paper, we propose a novel geometric-based approach called Tangent Attack (TA), which identifies an optimal tangent point of a virtual hemisphere located on the decision boundary to reduce the distortion of the attack.

Hard-label Attack

Aesthetic Photo Collage with Deep Reinforcement Learning

no code implementations19 Oct 2021 Mingrui Zhang, Mading Li, Li Chen, Jiahao Yu

To overcome the lack of training data, we pretrain our deep aesthetic network on a large scale image aesthetic dataset (CPC) for general aesthetic feature extraction and propose an attention fusion module for structural collage feature representation.

reinforcement-learning Reinforcement Learning (RL)

Reversible Attack based on Local Visual Adversarial Perturbation

no code implementations6 Oct 2021 Li Chen, Shaowei Zhu, Zhaoxia Yin

Adding perturbations to images can mislead classification models to produce incorrect results.

Adversarial Attack Autonomous Driving +2

Meta-learning an Intermediate Representation for Few-shot Block-wise Prediction of Landslide Susceptibility

1 code implementation3 Oct 2021 Li Chen, Yulin Ding, Saeid Pirasteh, Han Hu, Qing Zhu, Haowei Zeng, Haojia Yu, Qisen Shang, Yongfei Song

Then, the critical problem is that in each block with limited samples, conducting training and testing a model is impossible for a satisfactory LSM prediction, especially in dangerous mountainous areas where landslide surveying is expensive.

Meta-Learning

ERNIE-SPARSE: Robust Efficient Transformer Through Hierarchically Unifying Isolated Information

no code implementations29 Sep 2021 Yang Liu, Jiaxiang Liu, Yuxiang Lu, Shikun Feng, Yu Sun, Zhida Feng, Li Chen, Hao Tian, Hua Wu, Haifeng Wang

The first factor is information bottleneck sensitivity, which is caused by the key feature of Sparse Transformer — only a small number of global tokens can attend to all other tokens.

text-classification Text Classification

Alpha at SemEval-2021 Task 6: Transformer Based Propaganda Classification

no code implementations SEMEVAL 2021 Zhida Feng, Jiji Tang, Jiaxiang Liu, Weichong Yin, Shikun Feng, Yu Sun, Li Chen

This paper describes our system participated in Task 6 of SemEval-2021: the task focuses on multimodal propaganda technique classification and it aims to classify given image and text into 22 classes.

Classification

Decentralized Federated Learning: Balancing Communication and Computing Costs

1 code implementation26 Jul 2021 Wei Liu, Li Chen, Wenyi Zhang

The performance of decentralized SGD is jointly influenced by inter-node communications and local updates.

Federated Learning

Deep Open Snake Tracker for Vessel Tracing

no code implementations19 Jul 2021 Li Chen, Wenjin Liu, Niranjan Balu, Mahmud Mossa-Basha, Thomas S. Hatsukami, Jenq-Neng Hwang, Chun Yuan

Vessel tracing by modeling vascular structures in 3D medical images with centerlines and radii can provide useful information for vascular health.

An Efficient Cervical Whole Slide Image Analysis Framework Based on Multi-scale Semantic and Location Deep Features

1 code implementation29 Jun 2021 Ziquan Wei, Shenghua Cheng, Junbo Hu, Li Chen, Shaoqun Zeng, Xiuli Liu

Digital gigapixel whole slide image (WSI) is widely used in clinical diagnosis, and automated WSI analysis is key for computer-aided diagnosis.

$\ell_2$-norm Flow Diffusion in Near-Linear Time

no code implementations30 May 2021 Li Chen, Richard Peng, Di Wang

Diffusion is a fundamental graph procedure and has been a basic building block in a wide range of theoretical and empirical applications such as graph partitioning and semi-supervised learning on graphs.

Clustering Graph Clustering +3

Towards a Better Understanding of Linear Models for Recommendation

no code implementations27 May 2021 Ruoming Jin, Dong Li, Jing Gao, Zhi Liu, Li Chen, Yang Zhou

Through the derivation and analysis of the closed-form solutions for two basic regression and matrix factorization approaches, we found these two approaches are indeed inherently related but also diverge in how they "scale-down" the singular values of the original user-item interaction matrix.

regression

Personalized Transformer for Explainable Recommendation

1 code implementation ACL 2021 Lei LI, Yongfeng Zhang, Li Chen

Transformer, which is demonstrated with strong language modeling capability, however, is not personalized and fails to make use of the user and item IDs since the ID tokens are not even in the same semantic space as the words.

Explainable Recommendation Language Modelling +1

Improving Robustness for Pose Estimation via Stable Heatmap Regression

no code implementations8 May 2021 Yumeng Zhang, Li Chen, Yufeng Liu, Xiaoyan Guo, Wen Zheng, Junhai Yong

Deep learning methods have achieved excellent performance in pose estimation, but the lack of robustness causes the keypoints to change drastically between similar images.

Pose Estimation regression

Designing Heaven's Will: The job assignment in the Chinese imperial civil service

no code implementations6 May 2021 Inácio Bó, Li Chen

We provide an original analysis of historical documents to describe the assignment procedures used to allocate entry-level civil service jobs in China from the tenth to the early twentieth century.

Hermite Polynomial-based Valuation of American Options with General Jump-Diffusion Processes

no code implementations24 Apr 2021 Li Chen, Guang Zhang

We present a new approximation scheme for the price and exercise policy of American options.

On the Robustness of Monte Carlo Dropout Trained with Noisy Labels

no code implementations22 Mar 2021 Purvi Goel, Li Chen

The memorization effect of deep learning hinders its performance to effectively generalize on test set when learning with noisy labels.

Learning with noisy labels Memorization

EXTRA: Explanation Ranking Datasets for Explainable Recommendation

1 code implementation20 Feb 2021 Lei LI, Yongfeng Zhang, Li Chen

To achieve a standard way of evaluating recommendation explanations, we provide three benchmark datasets for EXplanaTion RAnking (denoted as EXTRA), on which explainability can be measured by ranking-oriented metrics.

Explainable Models Explainable Recommendation +1

On the Relationship between Explanation and Recommendation: Learning to Rank Explanations for Improved Performance

2 code implementations1 Feb 2021 Lei LI, Yongfeng Zhang, Li Chen

Explaining to users why some items are recommended is critical, as it can help users to make better decisions, increase their satisfaction, and gain their trust in recommender systems (RS).

Learning-To-Rank Recommendation Systems

Blind Diagnosis for Millimeter-wave Large-scale Antenna Systems

no code implementations25 Jan 2021 Rui Sun, Weidong Wang, Li Chen, Guo Wei, Wenyi Zhang

Millimeter-wave (mmWave) communication systems rely on large-scale antenna arrays to combat large path-loss at mmWave band.

Diagnosis of Intelligent Reflecting Surface in Millimeter-wave Communication Systems

1 code implementation11 Jan 2021 Rui Sun, Weidong Wang, Li Chen, Guo Wei, Wenyi Zhang

In the second case where only partial CSI is available, we jointly exploit the sparsity of the millimeter-wave channel and the failure, and adopt compressed sparse and low-rank matrix recovery algorithm to decouple channel and failure.

Robust Deep Learning with Active Noise Cancellation for Spatial Computing

no code implementations16 Nov 2020 Li Chen, David Yang, Purvi Goel, Ilknur Kabul

This paper proposes CANC, a Co-teaching Active Noise Cancellation method, applied in spatial computing to address deep learning trained with extreme noisy labels.

Retrieval

CS2-Net: Deep Learning Segmentation of Curvilinear Structures in Medical Imaging

1 code implementation15 Oct 2020 Lei Mou, Yitian Zhao, Huazhu Fu, Yonghuai Liu, Jun Cheng, Yalin Zheng, Pan Su, Jianlong Yang, Li Chen, Alejandro F Frang, Masahiro Akiba, Jiang Liu

Automated detection of curvilinear structures, e. g., blood vessels or nerve fibres, from medical and biomedical images is a crucial early step in automatic image interpretation associated to the management of many diseases.

Decoder Management +1

Local Label Point Correction for Edge Detection of Overlapping Cervical Cells

1 code implementation5 Oct 2020 Jiawei Liu, Huijie Fan, Qiang Wang, Wentao Li, Yandong Tang, Danbo Wang, Mingyi Zhou, Li Chen

The qualitative and quantitative experimental results show that our LLPC can improve the quality of manual labels and the accuracy of overlapping cell edge detection.

Cell Segmentation Edge Detection +2

RS-MetaNet: Deep meta metric learning for few-shot remote sensing scene classification

no code implementations28 Sep 2020 Haifeng Li, Zhenqi Cui, Zhiqing Zhu, Li Chen, Jiawei Zhu, Haozhe Huang, Chao Tao

On the one hand, RS-MetaNet raises the level of learning from the sample to the task by organizing training in a meta way, and it learns to learn a metric space that can well classify remote sensing scenes from a series of tasks.

General Classification Metric Learning +1

Generative Model without Prior Distribution Matching

no code implementations23 Sep 2020 Cong Geng, Jia Wang, Li Chen, Zhiyong Gao

Variational Autoencoder (VAE) and its variations are classic generative models by learning a low-dimensional latent representation to satisfy some prior distribution (e. g., Gaussian distribution).

Switching Transferable Gradient Directions for Query-Efficient Black-Box Adversarial Attacks

no code implementations15 Sep 2020 Chen Ma, Shuyu Cheng, Li Chen, Jun Zhu, Junhai Yong

In each iteration, SWITCH first tries to update the current sample along the direction of $\hat{\mathbf{g}}$, but considers switching to its opposite direction $-\hat{\mathbf{g}}$ if our algorithm detects that it does not increase the value of the attack objective function.

Adversarial Attack

Simulating Unknown Target Models for Query-Efficient Black-box Attacks

1 code implementation CVPR 2021 Chen Ma, Li Chen, Jun-Hai Yong

The meta-gradients of this loss are then computed and accumulated from multiple tasks to update the Simulator and subsequently improve generalization.

Knowledge Distillation Meta-Learning

Xiaomingbot: A Multilingual Robot News Reporter

no code implementations ACL 2020 Runxin Xu, Jun Cao, Mingxuan Wang, Jiaze Chen, Hao Zhou, Ying Zeng, Yu-Ping Wang, Li Chen, Xiang Yin, Xijin Zhang, Songcheng Jiang, Yuxuan Wang, Lei LI

This paper proposes the building of Xiaomingbot, an intelligent, multilingual and multimodal software robot equipped with four integral capabilities: news generation, news translation, news reading and avatar animation.

News Generation Translation +1

Automated Intracranial Artery Labeling using a Graph Neural Network and Hierarchical Refinement

1 code implementation11 Jul 2020 Li Chen, Thomas Hatsukami, Jenq-Neng Hwang, Chun Yuan

Automatically labeling intracranial arteries (ICA) with their anatomical names is beneficial for feature extraction and detailed analysis of intracranial vascular structures.

Graph Neural Network

Noise Robust TTS for Low Resource Speakers using Pre-trained Model and Speech Enhancement

no code implementations26 May 2020 Dongyang Dai, Li Chen, Yu-Ping Wang, Mu Wang, Rui Xia, Xuchen Song, Zhiyong Wu, Yuxuan Wang

Firstly, the speech synthesis model is pre-trained with both multi-speaker clean data and noisy augmented data; then the pre-trained model is adapted on noisy low-resource new speaker data; finally, by setting the clean speech condition, the model can synthesize the new speaker's clean voice.

Decoder Speech Enhancement +1

DAPnet: A Double Self-attention Convolutional Network for Point Cloud Semantic Labeling

1 code implementation18 Apr 2020 Li Chen, Zewei Xu, Yongjian Fu, Haozhe Huang, Shaowen Wang, Haifeng Li

The incorporation of the double self-attention module has an average of 7\% improvement on the pre-class accuracy.

A Survey on Conversational Recommender Systems

no code implementations1 Apr 2020 Dietmar Jannach, Ahtsham Manzoor, Wanling Cai, Li Chen

Recommender systems are software applications that help users to find items of interest in situations of information overload.

Chatbot Recommendation Systems

Content Adaptive and Error Propagation Aware Deep Video Compression

no code implementations ECCV 2020 Guo Lu, Chunlei Cai, Xiaoyun Zhang, Li Chen, Wanli Ouyang, Dong Xu, Zhiyong Gao

Therefore, the encoder is adaptive to different video contents and achieves better compression performance by reducing the domain gap between the training and testing datasets.

Decoder Video Compression

Blurry Video Frame Interpolation

1 code implementation CVPR 2020 Wang Shen, Wenbo Bao, Guangtao Zhai, Li Chen, Xiongkuo Min, Zhiyong Gao

Existing works reduce motion blur and up-convert frame rate through two separate ways, including frame deblurring and frame interpolation.

Deblurring Video Enhancement +1

Uniform Interpolation Constrained Geodesic Learning on Data Manifold

no code implementations12 Feb 2020 Cong Geng, Jia Wang, Li Chen, Wenbo Bao, Chu Chu, Zhiyong Gao

Based on this defined Riemannian metric, we introduce a constant speed loss and a minimizing geodesic loss to regularize the interpolation network to generate uniform interpolation along the learned geodesic on the manifold.

Translation

Fast Kernel k-means Clustering Using Incomplete Cholesky Factorization

no code implementations7 Feb 2020 Li Chen, Shuisheng Zhou, Jiajun Ma

The key idea of the proposed kernel $k$-means clustering using incomplete Cholesky factorization is that we approximate the entire kernel matrix by the product of a low-rank matrix and its transposition.

Clustering

Stable Sparse Subspace Embedding for Dimensionality Reduction

no code implementations7 Feb 2020 Li Chen, Shuizheng Zhou, Jiajun Ma

Although they adopt uniform sampling with replacement, due to large sampling variance, the number of non-zeros is uneven among rows of the projection matrix which is generated in one trial, and more data information may be lost after dimension reduction.

Dimensionality Reduction

Kalibre: Knowledge-based Neural Surrogate Model Calibration for Data Center Digital Twins

no code implementations29 Jan 2020 Ruihang Wang, Xin Zhou, Linsen Dong, Yonggang Wen, Rui Tan, Li Chen, Guan Wang, Feng Zeng

However, in the context of CFD, each search step requires long-lasting CFD model's iterated solving, rendering these approaches impractical with increased model complexity.

Management

FFusionCGAN: An end-to-end fusion method for few-focus images using conditional GAN in cytopathological digital slides

1 code implementation3 Jan 2020 Xiebo Geng, Sibo Liua, Wei Han, Xu Li, Jiabo Ma, Jingya Yu, Xiuli Liu, Sahoqun Zeng, Li Chen, Shenghua Cheng

However, although existing image fusion techniques, including traditional algorithms and deep learning-based algorithms, can generate high-quality fused images, they need multiple images with different focus depths in the same field of view.

Generative Adversarial Network Semantic Segmentation +1

SCAttNet: Semantic Segmentation Network with Spatial and Channel Attention Mechanism for High-Resolution Remote Sensing Images

1 code implementation19 Dec 2019 Haifeng Li, Kaijian Qiu, Li Chen, Xiaoming Mei, Liang Hong, Chao Tao

High-resolution remote sensing images (HRRSIs) contain substantial ground object information, such as texture, shape, and spatial location.

Segmentation Semantic Segmentation

Reversible Adversarial Attack based on Reversible Image Transformation

no code implementations6 Nov 2019 Zhaoxia Yin, Hua Wang, Li Chen, Jie Wang, Weiming Zhang

In order to prevent illegal or unauthorized access of image data such as human faces and ensure legitimate users can use authorization-protected data, reversible adversarial attack technique is rise.

Adversarial Attack Image Restoration

Robust Federated Learning with Noisy Communication

no code implementations1 Nov 2019 Fan Ang, Li Chen, Nan Zhao, Yunfei Chen, Weidong Wang, F. Richard Yu

Nevertheless, it is impractical to achieve a perfect acquisition of the local models in wireless communication due to noise, which also brings serious effects on federated learning.

Federated Learning Robust Design

Adversarial Example in Remote Sensing Image Recognition

no code implementations29 Oct 2019 Li Chen, Guowei Zhu, Qi Li, Haifeng Li

This added adversarial perturbation image is called an adversarial example, which poses a serious security problem for systems based on CNN model recognition results.

Accelerating Federated Learning via Momentum Gradient Descent

no code implementations8 Oct 2019 Wei Liu, Li Chen, Yunfei Chen, Wenyi Zhang

The proposed momentum federated learning (MFL) uses momentum gradient descent (MGD) in the local update step of FL system.

BIG-bench Machine Learning Federated Learning

Self-Paced Video Data Augmentation with Dynamic Images Generated by Generative Adversarial Networks

no code implementations16 Sep 2019 Yumeng Zhang, Gaoguo Jia, Li Chen, Mingrui Zhang, Junhai Yong

The dynamic image compresses the motion information of video into a still image, removing the interference factors such as the background.

Data Augmentation General Classification +1

Adaptive Wasserstein Hourglass for Weakly Supervised Hand Pose Estimation from Monocular RGB

no code implementations11 Sep 2019 Yumeng Zhang, Li Chen, Yufeng Liu, Junhai Yong, Wen Zheng

During training, based on the relation between these common characteristics and 3D pose learned from fully-annotated synthetic datasets, it is beneficial for the network to restore the 3D pose of weakly labeled real-world datasets with the aid of 2D annotations and depth images.

3D Hand Pose Estimation Domain Adaptation

Multi-stage domain adversarial style reconstruction for cytopathological image stain normalization

no code implementations11 Sep 2019 Xihao Chen, Jingya Yu, Li Chen, Shaoqun Zeng, Xiuli Liu, Shenghua Cheng

This article proposes a new framework that normalizes the stain style for cytopathological images through a stain removal module and a multi-stage domain adversarial style reconstruction module.

regression

MetaAdvDet: Towards Robust Detection of Evolving Adversarial Attacks

1 code implementation6 Aug 2019 Chen Ma, Chenxu Zhao, Hailin Shi, Li Chen, Junhai Yong, Dan Zeng

To solve such few-shot problem with the evolving attack, we propose a meta-learning based robust detection method to detect new adversarial attacks with limited examples.

Adversarial Attack Detection Meta-Learning

User Validation of Recommendation Serendipity Metrics

no code implementations27 Jun 2019 Li Chen, Ningxia Wang, Yonghua Yang, Keping Yang, Quan Yuan

Though it has been recognized that recommending serendipitous (i. e., surprising and relevant) items can be helpful for increasing users' satisfaction and behavioral intention, how to measure serendipity in the offline environment is still an open issue.

An End-to-End Block Autoencoder For Physical Layer Based On Neural Networks

no code implementations15 Jun 2019 Tianjie Mu, Xiaohui Chen, Li Chen, Huarui Yin, Weidong Wang

Deep Learning has been widely applied in the area of image processing and natural language processing.

Information Theory Signal Processing Information Theory

Sparse Representation Classification via Screening for Graphs

no code implementations4 Jun 2019 Cencheng Shen, Li Chen, Yuexiao Dong, Carey Priebe

The sparse representation classifier (SRC) is shown to work well for image recognition problems that satisfy a subspace assumption.

Classification Classification Consistency +1

Privacy Preserving Adjacency Spectral Embedding on Stochastic Blockmodels

no code implementations16 May 2019 Li Chen

For graphs generated from stochastic blockmodels, adjacency spectral embedding is asymptotically consistent.

Privacy Preserving

To believe or not to believe: Validating explanation fidelity for dynamic malware analysis

no code implementations30 Apr 2019 Li Chen, Carter Yagemann, Evan Downing

For both case studies, we first train deep learning models via transfer learning on malware images, demonstrate high classification effectiveness, apply an explanation method on the images, and correlate the results back to the samples to validate whether the algorithmic insights are consistent with security domain expertise.

Classification General Classification +3

Ranking-Based Autoencoder for Extreme Multi-label Classification

no code implementations NAACL 2019 Bingyu Wang, Li Chen, Wei Sun, Kechen Qin, Kefeng Li, Hui Zhou

Extreme Multi-label classification (XML) is an important yet challenging machine learning task, that assigns to each instance its most relevant candidate labels from an extremely large label collection, where the numbers of labels, features and instances could be thousands or millions.

Classification Extreme Multi-Label Classification +2

The Efficacy of SHIELD under Different Threat Models

no code implementations1 Feb 2019 Cory Cornelius, Nilaksh Das, Shang-Tse Chen, Li Chen, Michael E. Kounavis, Duen Horng Chau

To evaluate the robustness of the defense against an adaptive attacker, we consider the targeted-attack success rate of the Projected Gradient Descent (PGD) attack, which is a strong gradient-based adversarial attack proposed in adversarial machine learning research.

Adversarial Attack Image Classification

Understanding the Importance of Single Directions via Representative Substitution

no code implementations20 Jan 2019 Li Chen, Hailun Ding, Qi Li, Zhuo Li, Jian Peng, Haifeng Li

Understanding the internal representations of deep neural networks (DNNs) is crucal to explain their behavior.

A Data-driven Adversarial Examples Recognition Framework via Adversarial Feature Genome

no code implementations25 Dec 2018 Li Chen, Qi Li, Weiye Chen, Zeyu Wang, Haifeng Li

In this regard, we propose the Adversarial Feature Genome (AFG), a novel type of data that contains both the differences and features about classes.

General Classification Multi-Label Classification

Towards resilient machine learning for ransomware detection

no code implementations21 Dec 2018 Li Chen, Chih-Yuan Yang, Anindya Paul, Ravi Sahita

In this case study, we propose to use GAN to automatically produce dynamic features that exhibit generalized malicious behaviors that can reduce the efficacy of black-box ransomware classifiers.

BIG-bench Machine Learning Generative Adversarial Network +1

Deep Transfer Learning for Static Malware Classification

1 code implementation18 Dec 2018 Li Chen

In the transfer learning scheme, we borrow knowledge from natural images or objects and apply to the target domain of static malware detection.

Binary Classification Classification +3

AU R-CNN: Encoding Expert Prior Knowledge into R-CNN for Action Unit Detection

2 code implementations14 Dec 2018 Chen Ma, Li Chen, Junhai Yong

(2) We integrate various dynamic models (including convolutional long short-term memory, two stream network, conditional random field, and temporal action localization network) into AU R-CNN and then investigate and analyze the reason behind the performance of dynamic models.

Action Unit Detection Temporal Action Localization

Post: Device Placement with Cross-Entropy Minimization and Proximal Policy Optimization

no code implementations NeurIPS 2018 Yuanxiang Gao, Li Chen, Baochun Li

It is critical to place operations in a neural network on these devices in an optimal way, so that the training process can complete within the shortest amount of time.

Understanding the Importance of Single Directions via Representative Substitution

no code implementations27 Nov 2018 Li Chen, Hailun Ding, Qi Li, Zhuo Li, Jian Peng, Haifeng Li

Understanding the internal representations of deep neural networks (DNNs) is crucal to explain their behavior.

Spotlight: Optimizing Device Placement for Training Deep Neural Networks

no code implementations ICML 2018 Yuanxiang Gao, Li Chen, Baochun Li

Training deep neural networks (DNNs) requires an increasing amount of computation resources, and it becomes typical to use a mixture of GPU and CPU devices.

reinforcement-learning Reinforcement Learning (RL)

ADAGIO: Interactive Experimentation with Adversarial Attack and Defense for Audio

no code implementations30 May 2018 Nilaksh Das, Madhuri Shanbhogue, Shang-Tse Chen, Li Chen, Michael E. Kounavis, Duen Horng Chau

Adversarial machine learning research has recently demonstrated the feasibility to confuse automatic speech recognition (ASR) models by introducing acoustically imperceptible perturbations to audio samples.

Adversarial Attack Audio Compression +3