Search Results for author: Jing Xu

Found 63 papers, 18 papers with code

A Systematic Evaluation of Backdoor Trigger Characteristics in Image Classification

no code implementations3 Feb 2023 Gorka Abad, Jing Xu, Stefanos Koffas, Behrad Tajalli, Stjepan Picek

Nevertheless, it is vulnerable to backdoor attacks that modify the training set to embed a secret functionality in the trained model.

Image Classification Transfer Learning

A Closer Look at Few-shot Classification Again

no code implementations28 Jan 2023 Xu Luo, Hao Wu, Ji Zhang, Lianli Gao, Jing Xu, Jingkuan Song

Few-shot classification consists of a training phase where a model is learned on a relatively large dataset and an adaptation phase where the learned model is adapted to previously-unseen tasks with limited labeled samples.

Classification Representation Learning +1

Faster Gradient-Free Algorithms for Nonsmooth Nonconvex Stochastic Optimization

no code implementations16 Jan 2023 Lesi Chen, Jing Xu, Luo Luo

We consider the optimization problem of the form $\min_{x \in \mathbb{R}^d} f(x) \triangleq \mathbb{E}_{\xi} [F(x; \xi)]$, where the component $F(x;\xi)$ is $L$-mean-squared Lipschitz but possibly nonconvex and nonsmooth.

Stochastic Optimization

On Bilevel Optimization without Lower-level Strong Convexity

no code implementations2 Jan 2023 Lesi Chen, Jing Xu, Jingzhao Zhang

Theoretical properties of bilevel problems are well studied when the lower-level problem is strongly convex.

Bilevel Optimization

TriPINet: Tripartite Progressive Integration Network for Image Manipulation Localization

no code implementations25 Dec 2022 Wei-Yun Liang, Jing Xu, Xiao Jin

In this paper, we propose a tripartite progressive integration network (TriPINet) for end-to-end image manipulation localization.

Image Forensics Image Manipulation

UperFormer: A Multi-scale Transformer-based Decoder for Semantic Segmentation

1 code implementation25 Nov 2022 Jing Xu, Wentao Shi, Pan Gao, Zhengwei Wang, Qizhu Li

On the more challenging ADE20K dataset, our best model yields a single-scale mIoU of 50. 18, and a multi-scale mIoU of 51. 8, which is on-par with the current state-of-art model, while we drastically cut the number of FLOPs by 53. 5%.

Object Localization Semantic Segmentation

The CRINGE Loss: Learning what language not to model

no code implementations10 Nov 2022 Leonard Adolphs, Tianyu Gao, Jing Xu, Kurt Shuster, Sainbayar Sukhbaatar, Jason Weston

Standard language model training employs gold human documents or human-human interaction data, and treats all training data as positive examples.

Language Modelling

Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the Centroid

1 code implementation30 Oct 2022 Jing Xu, Xu Luo, Xinglin Pan, Wenjie Pei, Yanan Li, Zenglin Xu

In this paper, we find that this problem usually occurs when the positions of support samples are in the vicinity of task centroid -- the mean of all class centroids in the task.

Few-Shot Learning Selection bias

When Life Gives You Lemons, Make Cherryade: Converting Feedback from Bad Responses into Good Labels

no code implementations28 Oct 2022 Weiyan Shi, Emily Dinan, Kurt Shuster, Jason Weston, Jing Xu

Deployed dialogue agents have the potential to integrate human feedback to continuously improve themselves.

Chatbot

Enhancing Generalizable 6D Pose Tracking of an In-Hand Object with Tactile Sensing

no code implementations8 Oct 2022 Xiaomeng Xu, Yun Liu, Weihang Chen, Haocheng Yuan, He Wang, Jing Xu, Rui Chen, Li Yi

To test our method in real scenarios and enable future studies on generalizable visual-tactile tracking, we collect a real visual-tactile in-hand object pose tracking dataset.

hand-object pose Pose Tracking

A Multi-turn Machine Reading Comprehension Framework with Rethink Mechanism for Emotion-Cause Pair Extraction

1 code implementation COLING 2022 Changzhi Zhou, Dandan song, Jing Xu, Zhijing Wu

Our framework can model complicated relations between emotions and causes while avoiding generating the pairing matrix (the leading cause of the label sparsity problem).

Emotion-Cause Pair Extraction Machine Reading Comprehension

Learning from data in the mixed adversarial non-adversarial case: Finding the helpers and ignoring the trolls

no code implementations5 Aug 2022 Da Ju, Jing Xu, Y-Lan Boureau, Jason Weston

The promise of interaction between intelligent conversational agents and humans is that models can learn from such feedback in order to improve.

BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage

1 code implementation5 Aug 2022 Kurt Shuster, Jing Xu, Mojtaba Komeili, Da Ju, Eric Michael Smith, Stephen Roller, Megan Ung, Moya Chen, Kushal Arora, Joshua Lane, Morteza Behrooz, William Ngan, Spencer Poff, Naman Goyal, Arthur Szlam, Y-Lan Boureau, Melanie Kambadur, Jason Weston

We present BlenderBot 3, a 175B parameter dialogue model capable of open-domain conversation with access to the internet and a long-term memory, and having been trained on a large number of user defined tasks.

Continual Learning

Learning New Skills after Deployment: Improving open-domain internet-driven dialogue with human feedback

no code implementations5 Aug 2022 Jing Xu, Megan Ung, Mojtaba Komeili, Kushal Arora, Y-Lan Boureau, Jason Weston

We then study various algorithms for improving from such feedback, including standard supervised learning, rejection sampling, model-guiding and reward-based learning, in order to make recommendations on which type of feedback and algorithms work best.

Retrieval

SSformer: A Lightweight Transformer for Semantic Segmentation

1 code implementation3 Aug 2022 Wentao Shi, Jing Xu, Pan Gao

It is well believed that Transformer performs better in semantic segmentation compared to convolutional neural networks.

Image Classification Semantic Segmentation

Channel Importance Matters in Few-Shot Image Classification

1 code implementation16 Jun 2022 Xu Luo, Jing Xu, Zenglin Xu

When facing novel few-shot tasks in the test-time datasets, this transformation can greatly improve the generalization ability of learned image representations, while being agnostic to the choice of training algorithms and datasets.

Few-Shot Image Classification

Freeform Body Motion Generation from Speech

1 code implementation4 Mar 2022 Jing Xu, Wei zhang, Yalong Bai, Qibin Sun, Tao Mei

Motivated by studies in linguistics, we decompose the co-speech motion into two complementary parts: pose modes and rhythmic dynamics.

Semantically Proportional Patchmix for Few-Shot Learning

no code implementations17 Feb 2022 Jingquan Wang, Jing Xu, Yu Pan, Zenglin Xu

Few-shot learning aims to classify unseen classes with only a limited number of labeled data.

Few-Shot Learning Transfer Learning

When do Models Generalize? A Perspective from Data-Algorithm Compatibility

no code implementations12 Feb 2022 Jing Xu, Jiaye Teng, Yang Yuan, Andrew Chi-Chih Yao

By considering the entire training trajectory and focusing on early-stopping iterates, compatibility exploits the data and the algorithm information and is therefore a more suitable notion for generalization.

Generalization Bounds Learning Theory

More is Better (Mostly): On the Backdoor Attacks in Federated Graph Neural Networks

no code implementations7 Feb 2022 Jing Xu, Rui Wang, Stefanos Koffas, Kaitai Liang, Stjepan Picek

We find that both attacks are robust against the investigated defenses, necessitating the need to consider backdoor attacks in Federated GNNs as a novel threat that requires custom defenses.

Federated Learning Privacy Preserving

Exploring Category-correlated Feature for Few-shot Image Classification

no code implementations14 Dec 2021 Jing Xu, Xinglin Pan, Xu Luo, Wenjie Pei, Zenglin Xu

To alleviate this problem, we present a simple yet effective feature rectification method by exploring the category correlation between novel and base classes as the prior knowledge.

Classification Few-Shot Image Classification

Watermarking Graph Neural Networks based on Backdoor Attacks

no code implementations21 Oct 2021 Jing Xu, Stefanos Koffas, Oguzhan Ersoy, Stjepan Picek

The experiments show that our framework can verify the ownership of GNN models with a very high probability (up to $99\%$) for both tasks.

Classification Graph Classification +2

ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mind

1 code implementation NeurIPS 2021 Yuanfei Wang, Fangwei Zhong, Jing Xu, Yizhou Wang

With ToM, each agent is capable of inferring the mental states and intentions of others according to its (local) observation.

Boosting Graph Search with Attention Network for Solving the General Orienteering Problem

no code implementations10 Sep 2021 Zongtao Liu, Jing Xu, Jintao Su, Tao Xiao, Yang Yang

We propose a novel combination of a variant beam search algorithm and a learned heuristic for solving the general orienteering problem.

Boosting Salient Object Detection with Transformer-based Asymmetric Bilateral U-Net

1 code implementation17 Aug 2021 Yu Qiu, Yun Liu, Le Zhang, Jing Xu

The asymmetric bilateral encoder has a transformer path and a lightweight CNN path, where the two paths communicate at each encoder stage to learn complementary global contexts and local spatial details, respectively.

object-detection Object Detection +1

Can You Hear It? Backdoor Attacks via Ultrasonic Triggers

no code implementations30 Jul 2021 Stefanos Koffas, Jing Xu, Mauro Conti, Stjepan Picek

This work explores backdoor attacks for automatic speech recognition systems where we inject inaudible triggers.

Automatic Speech Recognition Backdoor Attack +1

Beyond Goldfish Memory: Long-Term Open-Domain Conversation

no code implementations ACL 2022 Jing Xu, Arthur Szlam, Jason Weston

Despite recent improvements in open-domain dialogue models, state of the art models are trained and evaluated on short conversations with little context.

Retrieval

FedCM: Federated Learning with Client-level Momentum

no code implementations21 Jun 2021 Jing Xu, Sen Wang, LiWei Wang, Andrew Chi-Chih Yao

Federated Learning is a distributed machine learning approach which enables model training without data sharing.

Federated Learning

On Anytime Learning at Macroscale

1 code implementation17 Jun 2021 Lucas Caccia, Jing Xu, Myle Ott, Marc'Aurelio Ranzato, Ludovic Denoyer

Practitioners have then to decide how to allocate their computational budget in order to obtain the best performance at any point in time.

Language Modelling Learning Theory

Bot-Adversarial Dialogue for Safe Conversational Agents

no code implementations NAACL 2021 Jing Xu, Da Ju, Margaret Li, Y-Lan Boureau, Jason Weston, Emily Dinan

Conversational agents trained on large unlabeled corpora of human interactions will learn patterns and mimic behaviors therein, which include offensive or otherwise toxic behavior.

Improving Facial Attribute Recognition by Group and Graph Learning

no code implementations28 May 2021 Zhenghao Chen, Shuhang Gu, Feng Zhu, Jing Xu, Rui Zhao

For the spatial correlation, we aggregate attributes with spatial similarity into a part-based group and then introduce a Group Attention Learning to generate the group attention and the part-based group feature.

Graph Learning

AFINet: Attentive Feature Integration Networks for Image Classification

no code implementations10 May 2021 Xinglin Pan, Jing Xu, Yu Pan, Liangjian Wen, WenXiang Lin, Kun Bai, Zenglin Xu

Convolutional Neural Networks (CNNs) have achieved tremendous success in a number of learning tasks including image classification.

Classification General Classification +1

Noise Attention based Spectrum Anomaly Detection Method for Unauthorized Bands

no code implementations17 Apr 2021 Jing Xu, Yu Tian, Shuai Yuan, Naijin Liu

In this paper, a noise attention method is proposed for unsupervised spectrum anomaly detection in unauthorized bands.

Anomaly Detection

Optically reconfigurable quantum spin-valley Hall effect of light in coupled nonlinear ring resonator lattice

no code implementations17 Feb 2021 Haofan Yang, Jing Xu, Zhongfei Xiong, Xinda Lu, Ruo-Yang Zhang, Yuntian Chen, Shuang Zhang

In optics, various photonic topological circuits have been developed, which were based on classical emulation of either quantum spin Hall effect or quantum valley Hall effect.

Optics

MultiFace: A Generic Training Mechanism for Boosting Face Recognition Performance

1 code implementation25 Jan 2021 Jing Xu, Tszhang Guo, Yong Xu, Zenglin Xu, Kun Bai

Deep Convolutional Neural Networks (DCNNs) and their variants have been widely used in large scale face recognition(FR) recently.

Face Recognition

Non-Ohmic negative longitudinal magnetoresistance in two-dimensional electron gas

no code implementations21 Jan 2021 Yang-Yang Lyu, Xian-Jing Zhou, Zhi-Li Xiao, Roxanna Fotovat, Jing Xu, Gobind Basnet, Yong-Lei Wang, Dafei Jin, Ralu Divan, Hua-Bing Wang, Wai-Kwong Kwok

Negative longitudinal magnetoresistance (NLMR) has been reported in a variety of materials and has attracted extensive attention as an electrotransport hallmark of topological Weyl semimetals.

Materials Science Mesoscale and Nanoscale Physics

Learning Contextual Perturbation Budgets for Training Robust Neural Networks

no code implementations1 Jan 2021 Jing Xu, Zhouxing Shi, huan zhang, JinFeng Yi, Cho-Jui Hsieh, LiWei Wang

We also demonstrate that the perturbation budget generator can produce semantically-meaningful budgets, which implies that the generator can capture contextual information and the sensitivity of different features in a given image.

AFINets: Attentive Feature Integration Networks for Image Classification

no code implementations1 Jan 2021 Xinglin Pan, Jing Xu, Yu Pan, WenXiang Lin, Liangjian Wen, Zenglin Xu

Convolutional Neural Networks (CNNs) have achieved tremendous success in a number of learning tasks, e. g., image classification.

Classification General Classification +1

Learning Multi-Agent Coordination for Enhancing Target Coverage in Directional Sensor Networks

1 code implementation NeurIPS 2020 Jing Xu, Fangwei Zhong, Yizhou Wang

Maximum target coverage by adjusting the orientation of distributed sensors is an important problem in directional sensor networks (DSNs).

Recipes for Safety in Open-domain Chatbots

no code implementations14 Oct 2020 Jing Xu, Da Ju, Margaret Li, Y-Lan Boureau, Jason Weston, Emily Dinan

Models trained on large unlabeled corpora of human interactions will learn patterns and mimic behaviors therein, which include offensive or otherwise toxic behavior and unwanted biases.

Integrated Communication and Localization in mmWave Systems

no code implementations28 Sep 2020 Jie Yang, Jing Xu, Xiao Li, Shi Jin, Bo Gao

As the fifth-generation (5G) mobile communication system is being commercialized, extensive studies on the evolution of 5G and sixth-generation mobile communication systems have been conducted.

Optimization-driven Hierarchical Learning Framework for Wireless Powered Backscatter-aided Relay Communications

no code implementations4 Aug 2020 Shimin Gong, Yuze Zou, Jing Xu, Dinh Thai Hoang, Bin Lyu, Dusit Niyato

In this paper, we employ multiple wireless-powered relays to assist information transmission from a multi-antenna access point to a single-antenna receiver.

Angular Triplet Loss-based Camera Network for ReID

no code implementations12 May 2020 Yitian Li, Ruini Xue, Mengmeng Zhu, Jing Xu, Zenglin Xu

Many complex network structures are proposed recently and many of them concentrate on multi-branch features to achieve high performance.

Person Re-Identification Retrieval

MiniSeg: An Extremely Minimum Network for Efficient COVID-19 Segmentation

1 code implementation21 Apr 2020 Yu Qiu, Yun Liu, Shijie Li, Jing Xu

On the other hand, fast training/testing and low computational cost are also necessary for quick deployment and development of COVID-19 screening systems, but traditional deep learning methods are usually computationally intensive.

COVID-19 Diagnosis Semantic Segmentation

Pose-Assisted Multi-Camera Collaboration for Active Object Tracking

no code implementations15 Jan 2020 Jing Li, Jing Xu, Fangwei Zhong, Xiangyu Kong, Yu Qiao, Yizhou Wang

In the system, each camera is equipped with two controllers and a switcher: The vision-based controller tracks targets based on observed images.

Object Tracking

S4G: Amodal Single-view Single-Shot SE(3) Grasp Detection in Cluttered Scenes

no code implementations31 Oct 2019 Yuzhe Qin, Rui Chen, Hao Zhu, Meng Song, Jing Xu, Hao Su

Grasping is among the most fundamental and long-lasting problems in robotics study.

Point-Based Multi-View Stereo Network

1 code implementation ICCV 2019 Rui Chen, Songfang Han, Jing Xu, Hao Su

More specifically, our method predicts the depth in a coarse-to-fine manner.

Compressing Recurrent Neural Networks with Tensor Ring for Action Recognition

1 code implementation NIPS Workshop CDNNRIA 2018 Yu Pan, Jing Xu, Maolin Wang, Jinmian Ye, Fei Wang, Kun Bai, Zenglin Xu

Recurrent Neural Networks (RNNs) and their variants, such as Long-Short Term Memory (LSTM) networks, and Gated Recurrent Unit (GRU) networks, have achieved promising performance in sequential data modeling.

Action Recognition Tensor Decomposition

The Function Transformation Omics - Funomics

no code implementations17 Aug 2018 Yongshuai Jiang, Jing Xu, Simeng Hu, Di Liu, Linna Zhao, Xu Zhou

Function transformation, such as f(x, y) and f(x, y, z), can transform two, three, or multiple input/observation variables (in biology, it generally refers to the observed/measured value of biomarkers, biological characteristics, or other indicators) into a new output variable (new characteristics or indicators).

Deep Boosting: Layered Feature Mining for General Image Classification

no code implementations3 Feb 2015 Zhanglin Peng, Liang Lin, Ruimao Zhang, Jing Xu

Constructing effective representations is a critical but challenging problem in multimedia understanding.

Classification General Classification +1

Intrusion Detection using Continuous Time Bayesian Networks

no code implementations16 Jan 2014 Jing Xu, Christian R. Shelton

For HIDS, we develop a novel learning method to deal with the finite resolution of system log file time stamps, without losing the benefits of our continuous time model.

Anomaly Detection Intrusion Detection

How memory biases affect information transmission: A rational analysis of serial reproduction

no code implementations NeurIPS 2008 Jing Xu, Thomas L. Griffiths

Many human interactions involve pieces of information being passed from one person to another, raising the question of how this process of information transmission is affected by the capacities of the agents involved.

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