Search Results for author: Cong Liu

Found 90 papers, 33 papers with code

Practical Poisoning Attacks on Neural Networks

no code implementations ECCV 2020 Junfeng Guo, Cong Liu

Importantly, we show that the effectiveness of BlackCard can be intuitively guaranteed by a set of analytical reasoning and observations, through exploiting an essential characteristic of gradient-descent optimization which is pervasively adopted in DNN models.

Data Poisoning

Assessing the Utility of Large Language Models for Phenotype-Driven Gene Prioritization in Rare Genetic Disorder Diagnosis

no code implementations21 Mar 2024 Junyoung Kim, Jingye Yang, Kai Wang, Chunhua Weng, Cong Liu

A similar increasing trend was observed for the task completion rate, with complicated prompts more likely to increase task completeness in models smaller than GPT-4.

Knowledge Graphs

Clifford Group Equivariant Simplicial Message Passing Networks

1 code implementation15 Feb 2024 Cong Liu, David Ruhe, Floor Eijkelboom, Patrick Forré

Experimental results show that our method is able to outperform both equivariant and simplicial graph neural networks on a variety of geometric tasks.

Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation

1 code implementation31 Jan 2024 Maoyuan Ye, Jing Zhang, Juhua Liu, Chenyu Liu, BaoCai Yin, Cong Liu, Bo Du, DaCheng Tao

In terms of the AMG mode, Hi-SAM segments text stroke foreground masks initially, then samples foreground points for hierarchical text mask generation and achieves layout analysis in passing.

Hierarchical Text Segmentation Segmentation +1

PPM: Automated Generation of Diverse Programming Problems for Benchmarking Code Generation Models

no code implementations28 Jan 2024 Simin Chen, Xiaoning Feng, Xiaohong Han, Cong Liu, Wei Yang

In recent times, a plethora of Large Code Generation Models (LCGMs) have been proposed, showcasing significant potential in assisting developers with complex programming tasks.

Benchmarking Code Generation

The stability and instability of the language control network: a longitudinal resting-state functional magnetic resonance imaging study

no code implementations23 Jan 2024 Zilong Li, Cong Liu, Xin Pan, Guosheng Ding, Ruiming Wang

These findings provide preliminary evidence of the coexistence of stability and instability in the language control network.

Uncertainty Awareness of Large Language Models Under Code Distribution Shifts: A Benchmark Study

1 code implementation12 Jan 2024 Yufei Li, Simin Chen, Yanghong Guo, Wei Yang, Yue Dong, Cong Liu

We observe that these methods generally improve the uncertainty awareness of CodeLlama, with increased calibration quality and higher uncertainty estimation~(UE) precision.

GestaltMML: Enhancing Rare Genetic Disease Diagnosis through Multimodal Machine Learning Combining Facial Images and Clinical Texts

no code implementations23 Dec 2023 Da Wu, Jingye Yang, Cong Liu, Tzung-Chien Hsieh, Elaine Marchi, Justin Blair, Peter Krawitz, Chunhua Weng, Wendy Chung, Gholson J. Lyon, Ian D. Krantz, Jennifer M. Kalish, Kai Wang

Many rare genetic diseases have distinctive facial features, which can be used by artificial intelligence algorithms to facilitate clinical diagnosis, in prioritizing candidate diseases to be further examined by lab tests or genetic assays, or in helping the phenotype-driven reinterpretation of genome/exome sequencing data.

Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context Attack

no code implementations12 Dec 2023 Yu Fu, Yufei Li, Wen Xiao, Cong Liu, Yue Dong

Recent developments in balancing the usefulness and safety of Large Language Models (LLMs) have raised a critical question: Are mainstream NLP tasks adequately aligned with safety consideration?

Question Answering

Generative Input: Towards Next-Generation Input Methods Paradigm

no code implementations2 Nov 2023 Keyu Ding, Yongcan Wang, Zihang Xu, Zhenzhen Jia, Shijin Wang, Cong Liu, Enhong Chen

The results demonstrate that we have achieved state-of-the-art performance for the first time in the Full-mode Key-sequence to Characters(FK2C) task.

1DFormer: a Transformer Architecture Learning 1D Landmark Representations for Facial Landmark Tracking

no code implementations1 Nov 2023 Shi Yin, Shijie Huan, Shangfei Wang, Jinshui Hu, Tao Guo, Bing Yin, BaoCai Yin, Cong Liu

For temporal modeling, we propose a recurrent token mixing mechanism, an axis-landmark-positional embedding mechanism, as well as a confidence-enhanced multi-head attention mechanism to adaptively and robustly embed long-term landmark dynamics into their 1D representations; for structure modeling, we design intra-group and inter-group structure modeling mechanisms to encode the component-level as well as global-level facial structure patterns as a refinement for the 1D representations of landmarks through token communications in the spatial dimension via 1D convolutional layers.

Landmark Tracking

Untying the Reversal Curse via Bidirectional Language Model Editing

1 code implementation16 Oct 2023 Jun-Yu Ma, Jia-Chen Gu, Zhen-Hua Ling, Quan Liu, Cong Liu

A new evaluation metric of reversibility is introduced, and a benchmark dubbed as Bidirectional Assessment for Knowledge Editing (BAKE) is constructed to evaluate the reversibility of edited models in recalling knowledge in the reverse direction of editing.

knowledge editing Language Modelling +1

Distantly-Supervised Joint Entity and Relation Extraction with Noise-Robust Learning

1 code implementation8 Oct 2023 Yufei Li, Xiao Yu, Yanghong Guo, Yanchi Liu, Haifeng Chen, Cong Liu

However, existing research primarily addresses only one type of noise, thereby limiting the effectiveness of noise reduction.

Joint Entity and Relation Extraction Relation

RT-LM: Uncertainty-Aware Resource Management for Real-Time Inference of Language Models

no code implementations12 Sep 2023 Yufei Li, Zexin Li, Wei Yang, Cong Liu

Recent advancements in language models (LMs) have gained substantial attentions on their capability to generate human-like responses.


GLAD: Content-aware Dynamic Graphs For Log Anomaly Detection

1 code implementation12 Sep 2023 Yufei Li, Yanchi Liu, Haoyu Wang, Zhengzhang Chen, Wei Cheng, Yuncong Chen, Wenchao Yu, Haifeng Chen, Cong Liu

Subsequently, GLAD utilizes a temporal-attentive graph edge anomaly detection model for identifying anomalous relations in these dynamic log graphs.

Anomaly Detection Few-Shot Learning

R^3: On-device Real-Time Deep Reinforcement Learning for Autonomous Robotics

no code implementations29 Aug 2023 Zexin Li, Aritra Samanta, Yufei Li, Andrea Soltoggio, Hyoseung Kim, Cong Liu

These components collaboratively tackle the trade-offs in on-device DRL training, improving timing and algorithm performance while minimizing the risk of out-of-memory (OOM) errors.

Autonomous Vehicles

RED: A Systematic Real-Time Scheduling Approach for Robotic Environmental Dynamics

no code implementations29 Aug 2023 Zexin Li, Tao Ren, Xiaoxi He, Cong Liu

This process ensures the scheduling framework's compatibility with MIMONet and maximizes efficiency.

Navigate Scheduling

4D Myocardium Reconstruction with Decoupled Motion and Shape Model

1 code implementation ICCV 2023 Xiaohan Yuan, Cong Liu, Yangang Wang

Estimating the shape and motion state of the myocardium is essential in diagnosing cardiovascular diseases. However, cine magnetic resonance (CMR) imaging is dominated by 2D slices, whose large slice spacing challenges inter-slice shape reconstruction and motion acquisition. To address this problem, we propose a 4D reconstruction method that decouples motion and shape, which can predict the inter-/intra- shape and motion estimation from a given sparse point cloud sequence obtained from limited slices.

4D reconstruction Motion Estimation

Enhancing Phenotype Recognition in Clinical Notes Using Large Language Models: PhenoBCBERT and PhenoGPT

1 code implementation11 Aug 2023 Jingye Yang, Cong Liu, Wendy Deng, Da Wu, Chunhua Weng, Yunyun Zhou, Kai Wang

We hypothesize that large language models (LLMs) based on the transformer architecture can enable automated detection of clinical phenotype terms, including terms not documented in the HPO.


Exploring Part-Informed Visual-Language Learning for Person Re-Identification

no code implementations4 Aug 2023 Yin Lin, Cong Liu, Yehansen Chen, Jinshui Hu, Bing Yin, BaoCai Yin, Zengfu Wang

Recently, visual-language learning has shown great potential in enhancing visual-based person re-identification (ReID).

Human Parsing Person Re-Identification

PIMbot: Policy and Incentive Manipulation for Multi-Robot Reinforcement Learning in Social Dilemmas

no code implementations29 Jul 2023 Shahab Nikkhoo, Zexin Li, Aritra Samanta, Yufei Li, Cong Liu

Our work introduces a new angle for manipulation in recent multi-agent RL social dilemmas that utilize a unique reward function for incentivization.

Reinforcement Learning (RL)

MIMONet: Multi-Input Multi-Output On-Device Deep Learning

no code implementations22 Jul 2023 Zexin Li, Xiaoxi He, Yufei Li, Shahab Nikkhoo, Wei Yang, Lothar Thiele, Cong Liu

In this paper, we propose MIMONet, a novel on-device multi-input multi-output (MIMO) DNN framework that achieves high accuracy and on-device efficiency in terms of critical performance metrics such as latency, energy, and memory usage.

Model Compression

DyCL: Dynamic Neural Network Compilation Via Program Rewriting and Graph Optimization

no code implementations11 Jul 2023 Simin Chen, Shiyi Wei, Cong Liu, Wei Yang

\tool tackles the dynamic nature of DyNNs by introducing a compilation mechanism that redistributes the control and data flow of the original DNN programs during the compilation process.

Bi-LRFusion: Bi-Directional LiDAR-Radar Fusion for 3D Dynamic Object Detection

1 code implementation CVPR 2023 Yingjie Wang, Jiajun Deng, Yao Li, Jinshui Hu, Cong Liu, Yu Zhang, Jianmin Ji, Wanli Ouyang, Yanyong Zhang

LiDAR and Radar are two complementary sensing approaches in that LiDAR specializes in capturing an object's 3D shape while Radar provides longer detection ranges as well as velocity hints.

object-detection Object Detection

SlothSpeech: Denial-of-service Attack Against Speech Recognition Models

1 code implementation1 Jun 2023 Mirazul Haque, Rutvij Shah, Simin Chen, Berrak Şişman, Cong Liu, Wei Yang

We show that popular ASR models like Speech2Text model and Whisper model have dynamic computation based on different inputs, causing dynamic efficiency.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

MADNet: Maximizing Addressee Deduction Expectation for Multi-Party Conversation Generation

1 code implementation22 May 2023 Jia-Chen Gu, Chao-Hong Tan, Caiyuan Chu, Zhen-Hua Ling, Chongyang Tao, Quan Liu, Cong Liu

Given an MPC with a few addressee labels missing, existing methods fail to build a consecutively connected conversation graph, but only a few separate conversation fragments instead.

SHINE: Syntax-augmented Hierarchical Interactive Encoder for Zero-shot Cross-lingual Information Extraction

no code implementations21 May 2023 Jun-Yu Ma, Jia-Chen Gu, Zhen-Hua Ling, Quan Liu, Cong Liu, Guoping Hu

The proposed encoder is capable of interactively capturing complementary information between features and contextual information, to derive language-agnostic representations for various IE tasks.

Dynamic Transformers Provide a False Sense of Efficiency

1 code implementation20 May 2023 Yiming Chen, Simin Chen, Zexin Li, Wei Yang, Cong Liu, Robby T. Tan, Haizhou Li

Despite much success in natural language processing (NLP), pre-trained language models typically lead to a high computational cost during inference.

Adversarial Attack

Sharing Lifelong Reinforcement Learning Knowledge via Modulating Masks

1 code implementation18 May 2023 Saptarshi Nath, Christos Peridis, Eseoghene Ben-Iwhiwhu, Xinran Liu, Shirin Dora, Cong Liu, Soheil Kolouri, Andrea Soltoggio

The key idea is that the isolation of specific task knowledge to specific masks allows agents to transfer only specific knowledge on-demand, resulting in robust and effective distributed lifelong learning.


GIFT: Graph-Induced Fine-Tuning for Multi-Party Conversation Understanding

1 code implementation16 May 2023 Jia-Chen Gu, Zhen-Hua Ling, Quan Liu, Cong Liu, Guoping Hu

Addressing the issues of who saying what to whom in multi-party conversations (MPCs) has recently attracted a lot of research attention.

Speaker Identification

TinyML Design Contest for Life-Threatening Ventricular Arrhythmia Detection

no code implementations9 May 2023 Zhenge Jia, Dawei Li, Cong Liu, Liqi Liao, Xiaowei Xu, Lichuan Ping, Yiyu Shi

This paper concludes with the direction of improvement for the future TinyML design for health monitoring applications.

Arrhythmia Detection

White-Box Multi-Objective Adversarial Attack on Dialogue Generation

1 code implementation5 May 2023 Yufei Li, Zexin Li, Yingfan Gao, Cong Liu

Such language models are, however, vulnerable to various adversarial samples as studied in traditional tasks such as text classification, which inspires our curiosity about their robustness in DG systems.

Adversarial Attack Decision Making +4

Uncertainty-Aware Bootstrap Learning for Joint Extraction on Distantly-Supervised Data

1 code implementation5 May 2023 Yufei Li, Xiao Yu, Yanchi Liu, Haifeng Chen, Cong Liu

To mitigate such impact, we propose uncertainty-aware bootstrap learning, which is motivated by the intuition that the higher uncertainty of an instance, the more likely the model confidence is inconsistent with the ground truths.

Relation Extraction

DocMAE: Document Image Rectification via Self-supervised Representation Learning

1 code implementation20 Apr 2023 Shaokai Liu, Hao Feng, Wengang Zhou, Houqiang Li, Cong Liu, Feng Wu

Tremendous efforts have been made on document image rectification, but how to learn effective representation of such distorted images is still under-explored.

Representation Learning Self-Supervised Learning

VGTS: Visually Guided Text Spotting for Novel Categories in Historical Manuscripts

no code implementations3 Apr 2023 WenBo Hu, Hongjian Zhan, Xinchen Ma, Cong Liu, Bing Yin, Yue Lu

In the field of historical manuscript research, scholars frequently encounter novel symbols in ancient texts, investing considerable effort in their identification and documentation.

Geometric Matching Metric Learning +4

HRDoc: Dataset and Baseline Method Toward Hierarchical Reconstruction of Document Structures

1 code implementation24 Mar 2023 Jiefeng Ma, Jun Du, Pengfei Hu, Zhenrong Zhang, Jianshu Zhang, Huihui Zhu, Cong Liu

Moreover, we proposed an encoder-decoder-based hierarchical document structure parsing system (DSPS) to tackle this problem.

Sibling-Attack: Rethinking Transferable Adversarial Attacks against Face Recognition

1 code implementation CVPR 2023 Zexin Li, Bangjie Yin, Taiping Yao, Juefeng Guo, Shouhong Ding, Simin Chen, Cong Liu

A hard challenge in developing practical face recognition (FR) attacks is due to the black-box nature of the target FR model, i. e., inaccessible gradient and parameter information to attackers.

Adversarial Attack Attribute +1

Masked Images Are Counterfactual Samples for Robust Fine-tuning

1 code implementation CVPR 2023 Yao Xiao, Ziyi Tang, Pengxu Wei, Cong Liu, Liang Lin

In this paper, based on causal analysis of the aforementioned problems, we propose a novel fine-tuning method, which uses masked images as counterfactual samples that help improve the robustness of the fine-tuning model.


X-Adv: Physical Adversarial Object Attacks against X-ray Prohibited Item Detection

1 code implementation19 Feb 2023 Aishan Liu, Jun Guo, Jiakai Wang, Siyuan Liang, Renshuai Tao, Wenbo Zhou, Cong Liu, Xianglong Liu, DaCheng Tao

In this paper, we take the first step toward the study of adversarial attacks targeted at X-ray prohibited item detection, and reveal the serious threats posed by such attacks in this safety-critical scenario.

Adversarial Attack

The Dark Side of Dynamic Routing Neural Networks: Towards Efficiency Backdoor Injection

no code implementations CVPR 2023 Simin Chen, Hanlin Chen, Mirazul Haque, Cong Liu, Wei Yang

Recent advancements in deploying deep neural networks (DNNs) on resource-constrained devices have generated interest in input-adaptive dynamic neural networks (DyNNs).

Adversarial Attack

PolicyCleanse: Backdoor Detection and Mitigation for Competitive Reinforcement Learning

no code implementations ICCV 2023 Junfeng Guo, Ang Li, Lixu Wang, Cong Liu

To ensure the security of RL agents against malicious backdoors, in this work, we propose the problem of Backdoor Detection in multi-agent RL systems, with the objective of detecting Trojan agents as well as the corresponding potential trigger actions, and further trying to mitigate their bad impact.

Machine Unlearning reinforcement-learning +1

Deep Hashing With Minimal-Distance-Separated Hash Centers

no code implementations CVPR 2023 Liangdao Wang, Yan Pan, Cong Liu, Hanjiang Lai, Jian Yin, Ye Liu

This paper presents an optimization method that finds hash centers with a constraint on the minimal distance between any pair of hash centers, which is non-trivial due to the non-convex nature of the problem.

Deep Hashing Image Retrieval +1

Fast Rule-Based Decoding: Revisiting Syntactic Rules in Neural Constituency Parsing

no code implementations16 Dec 2022 Tianyu Shi, Zhicheng Wang, Liyin Xiao, Cong Liu

Most recent studies on neural constituency parsing focus on encoder structures, while few developments are devoted to decoders.

Constituency Parsing

WIDER & CLOSER: Mixture of Short-channel Distillers for Zero-shot Cross-lingual Named Entity Recognition

1 code implementation7 Dec 2022 Jun-Yu Ma, Beiduo Chen, Jia-Chen Gu, Zhen-Hua Ling, Wu Guo, Quan Liu, Zhigang Chen, Cong Liu

In this study, a mixture of short-channel distillers (MSD) method is proposed to fully interact the rich hierarchical information in the teacher model and to transfer knowledge to the student model sufficiently and efficiently.

Cross-Lingual NER Domain Adaptation +3

Self-Supervised Audio-Visual Speech Representations Learning By Multimodal Self-Distillation

no code implementations6 Dec 2022 Jing-Xuan Zhang, Genshun Wan, Zhen-Hua Ling, Jia Pan, Jianqing Gao, Cong Liu

AV2vec has a student and a teacher module, in which the student performs a masked latent feature regression task using the multimodal target features generated online by the teacher.

Language Modelling

Order-sensitive Neural Constituency Parsing

no code implementations1 Nov 2022 Zhicheng Wang, Tianyu Shi, Liyin Xiao, Cong Liu

We propose a novel algorithm that improves on the previous neural span-based CKY decoder for constituency parsing.

Constituency Parsing

DeepPerform: An Efficient Approach for Performance Testing of Resource-Constrained Neural Networks

no code implementations10 Oct 2022 Simin Chen, Mirazul Haque, Cong Liu, Wei Yang

To ensure an AdNN satisfies the performance requirements of resource-constrained applications, it is essential to conduct performance testing to detect IDPBs in the AdNN.

JiuZhang: A Chinese Pre-trained Language Model for Mathematical Problem Understanding

1 code implementation13 Jun 2022 Wayne Xin Zhao, Kun Zhou, Zheng Gong, Beichen Zhang, Yuanhang Zhou, Jing Sha, Zhigang Chen, Shijin Wang, Cong Liu, Ji-Rong Wen

Considering the complex nature of mathematical texts, we design a novel curriculum pre-training approach for improving the learning of mathematical PLMs, consisting of both basic and advanced courses.

Language Modelling Math

Learning to Reverse DNNs from AI Programs Automatically

no code implementations20 May 2022 Simin Chen, Hamed Khanpour, Cong Liu, Wei Yang

With the privatization deployment of DNNs on edge devices, the security of on-device DNNs has raised significant concern.

NICGSlowDown: Evaluating the Efficiency Robustness of Neural Image Caption Generation Models

1 code implementation CVPR 2022 Simin Chen, Zihe Song, Mirazul Haque, Cong Liu, Wei Yang

To further understand such efficiency-oriented threats, we propose a new attack approach, NICGSlowDown, to evaluate the efficiency robustness of NICG models.

Caption Generation

Dynamic Group Transformer: A General Vision Transformer Backbone with Dynamic Group Attention

no code implementations8 Mar 2022 Kai Liu, Tianyi Wu, Cong Liu, Guodong Guo

To reduce the quadratic computation complexity caused by each query attending to all keys/values, various methods have constrained the range of attention within local regions, where each query only attends to keys/values within a hand-crafted window.

Image Classification Instance Segmentation +3

EREBA: Black-box Energy Testing of Adaptive Neural Networks

no code implementations12 Feb 2022 Mirazul Haque, Yaswanth Yadlapalli, Wei Yang, Cong Liu

The test inputs generated by EREBA can increase the energy consumption of AdNNs by 2, 000% compared to the original inputs.

PolicyCleanse: Backdoor Detection and Mitigation in Reinforcement Learning

no code implementations8 Feb 2022 Junfeng Guo, Ang Li, Cong Liu

To ensure the security of RL agents against malicious backdoors, in this work, we propose the problem of Backdoor Detection in a multi-agent competitive reinforcement learning system, with the objective of detecting Trojan agents as well as the corresponding potential trigger actions, and further trying to mitigate their Trojan behavior.

Machine Unlearning reinforcement-learning +1

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

AEVA: Black-box Backdoor Detection Using Adversarial Extreme Value Analysis

1 code implementation ICLR 2022 Junfeng Guo, Ang Li, Cong Liu

We approach this problem from the optimization perspective and show that the objective of backdoor detection is bounded by an adversarial objective.

TransSlowDown: Efficiency Attacks on Neural Machine Translation Systems

no code implementations29 Sep 2021 Simin Chen, Mirazul Haque, Zihe Song, Cong Liu, Wei Yang

To further the understanding of such efficiency-oriented threats and raise the community’s concern on the efficiency robustness of NMT systems, we propose a new attack approach, TranSlowDown, to test the efficiency robustness of NMT systems.

Machine Translation NMT +1

NODEAttack: Adversarial Attack on the Energy Consumption of Neural ODEs

no code implementations29 Sep 2021 Mirazul Haque, Simin Chen, Wasif Arman Haque, Cong Liu, Wei Yang

Unlike the memory cost, the energy consumption of the Neural ODEs during inference can be adaptive because of the adaptive nature of the ODE solvers.

Adversarial Attack Object Recognition

Automatically eliminating seam lines with Poisson editing in complex relative radiometric normalization mosaicking scenarios

no code implementations14 Jun 2021 Shiqi Liu, Jie Lian, Xuchen Zhan, Cong Liu, Yuze Tian, Hongwei Duan

Relative radiometric normalization (RRN) mosaicking among multiple remote sensing images is crucial for the downstream tasks, including map-making, image recognition, semantic segmentation, and change detection.

Change Detection Semantic Segmentation

Adv-Makeup: A New Imperceptible and Transferable Attack on Face Recognition

1 code implementation7 May 2021 Bangjie Yin, Wenxuan Wang, Taiping Yao, Junfeng Guo, Zelun Kong, Shouhong Ding, Jilin Li, Cong Liu

Deep neural networks, particularly face recognition models, have been shown to be vulnerable to both digital and physical adversarial examples.

Adversarial Attack Face Generation +2

Neural Mean Discrepancy for Efficient Out-of-Distribution Detection

no code implementations CVPR 2022 Xin Dong, Junfeng Guo, Ang Li, Wei-Te Ting, Cong Liu, H. T. Kung

Based upon this observation, we propose a novel metric called Neural Mean Discrepancy (NMD), which compares neural means of the input examples and training data.

General Classification Out-of-Distribution Detection +1

SAM-GAN: Self-Attention supporting Multi-stage Generative Adversarial Networks for text-to-image synthesis

no code implementations Neural Networks 2021 Dunlu Peng ∗, Wuchen Yang, Cong Liu, Shuairui Lü

With the self-attention mechanism, the model can establish the multi-level dependence of the image and fuse the sentence- and word-level visual-semantic vectors, to improve the quality of the generated image.

Image Generation Semantic Similarity +2

PredCoin: Defense against Query-based Hard-label Attack

no code implementations4 Feb 2021 Junfeng Guo, Yaswanth Yadlapalli, Thiele Lothar, Ang Li, Cong Liu

PredCoin poisons the gradient estimation step, an essential component of most QBHL attacks.

Hard-label Attack

AttackDist: Characterizing Zero-day Adversarial Samples by Counter Attack

no code implementations1 Jan 2021 Simin Chen, Zihe Song, Lei Ma, Cong Liu, Wei Yang

We first theoretically clarify under which condition AttackDist can provide a certified detecting performance, then show that a potential application of AttackDist is distinguishing zero-day adversarial examples without knowing the mechanisms of new attacks.

Tensor Completion via Convolutional Sparse Coding Regularization

no code implementations2 Dec 2020 Zhebin Wu, Tianchi Liao, Chuan Chen, Cong Liu, Zibin Zheng, Xiongjun Zhang

On the contrary, in the field of signal processing, Convolutional Sparse Coding (CSC) can provide a good representation of the high-frequency component of the image, which is generally associated with the detail component of the data.

CAVA: A Visual Analytics System for Exploratory Columnar Data Augmentation Using Knowledge Graphs

1 code implementation7 Sep 2020 Dylan Cashman, Shenyu Xu, Subhajit Das, Florian Heimerl, Cong Liu, Shah Rukh Humayoun, Michael Gleicher, Alex Endert, Remco Chang

In this paper, we present CAVA, a system that integrates data curation and data augmentation with the traditional data exploration and analysis tasks, enabling information foraging in-situ during analysis.

Data Augmentation Knowledge Graphs

Deep Partial Updating: Towards Communication Efficient Updating for On-device Inference

no code implementations6 Jul 2020 Zhongnan Qu, Cong Liu, Lothar Thiele

Emerging edge intelligence applications require the server to retrain and update deep neural networks deployed on remote edge nodes to leverage newly collected data samples.

PoisHygiene: Detecting and Mitigating Poisoning Attacks in Neural Networks

no code implementations24 Mar 2020 Junfeng Guo, Ting Wang, Cong Liu

Being able to detect and mitigate poisoning attacks, typically categorized into backdoor and adversarial poisoning (AP), is critical in enabling safe adoption of DNNs in many application domains.

Data Poisoning

PhysGAN: Generating Physical-World-Resilient Adversarial Examples for Autonomous Driving

no code implementations CVPR 2020 Zelun Kong, Junfeng Guo, Ang Li, Cong Liu

We compare PhysGAN with a set of state-of-the-art baseline methods including several of our self-designed ones, which further demonstrate the robustness and efficacy of our approach.

Autonomous Driving Image Classification

Episodic Training for Domain Generalization

2 code implementations ICCV 2019 Da Li, Jianshu Zhang, Yongxin Yang, Cong Liu, Yi-Zhe Song, Timothy M. Hospedales

In this paper, we build on this strong baseline by designing an episodic training procedure that trains a single deep network in a way that exposes it to the domain shift that characterises a novel domain at runtime.

Domain Generalization

DeepBillboard: Systematic Physical-World Testing of Autonomous Driving Systems

no code implementations27 Dec 2018 Husheng Zhou, Wei Li, Yuankun Zhu, Yuqun Zhang, Bei Yu, Lingming Zhang, Cong Liu

Furthermore, DeepBillboard is sufficiently robust and resilient for generating physical-world adversarial billboard tests for real-world driving under various weather conditions.

Autonomous Driving DNN Testing

DeepRoad: GAN-based Metamorphic Autonomous Driving System Testing

1 code implementation7 Feb 2018 Mengshi Zhang, Yuqun Zhang, Lingming Zhang, Cong Liu, Sarfraz Khurshid

In this paper, we propose DeepRoad, an unsupervised framework to automatically generate large amounts of accurate driving scenes to test the consistency of DNN-based autonomous driving systems across different scenes.

Software Engineering

BENCHIP: Benchmarking Intelligence Processors

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

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


Improved Word Embeddings with Implicit Structure Information

no code implementations COLING 2016 Jie Shen, Cong Liu

Distributed word representation is an efficient method for capturing semantic and syntactic word relations.

Dependency Parsing Language Modelling +5

Modelling Sentence Pairs with Tree-structured Attentive Encoder

1 code implementation COLING 2016 Yao Zhou, Cong Liu, Yan Pan

We describe an attentive encoder that combines tree-structured recursive neural networks and sequential recurrent neural networks for modelling sentence pairs.

Paraphrase Identification Question Selection +2

Feedforward Sequential Memory Networks: A New Structure to Learn Long-term Dependency

no code implementations28 Dec 2015 Shiliang Zhang, Cong Liu, Hui Jiang, Si Wei, Li-Rong Dai, Yu Hu

In this paper, we propose a novel neural network structure, namely \emph{feedforward sequential memory networks (FSMN)}, to model long-term dependency in time series without using recurrent feedback.

Language Modelling speech-recognition +3

A Divide-and-Conquer Method for Scalable Low-Rank Latent Matrix Pursuit

no code implementations CVPR 2013 Yan Pan, Hanjiang Lai, Cong Liu, Shuicheng Yan

To address this issue, we provide a scalable solution for large-scale low-rank latent matrix pursuit by a divide-andconquer method.

Event Detection Object Categorization

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