Search Results for author: Yang Zhang

Found 262 papers, 119 papers with code

Dual Attention Model for Citation Recommendation with Analyses on Explainability of Attention Mechanisms and Qualitative Experiments

no code implementations CL (ACL) 2022 Yang Zhang, Qiang Ma

A neural network model is designed to maximize the similarity between the embedding of the three inputs (local context words, section headers, and structural contexts) and the target citation appearing in the context.

Citation Recommendation

S$^2$ME: Spatial-Spectral Mutual Teaching and Ensemble Learning for Scribble-supervised Polyp Segmentation

1 code implementation1 Jun 2023 An Wang, Mengya Xu, Yang Zhang, Mobarakol Islam, Hongliang Ren

Furthermore, to produce reliable mixed pseudo labels, which enhance the effectiveness of ensemble learning, we introduce a novel adaptive pixel-wise fusion technique based on the entropy guidance from the spatial and spectral branches.

Ensemble Learning Image Segmentation +4

Long-term Wind Power Forecasting with Hierarchical Spatial-Temporal Transformer

no code implementations30 May 2023 Yang Zhang, Lingbo Liu, Xinyu Xiong, Guanbin Li, Guoli Wang, Liang Lin

In this work, we propose a novel end-to-end wind power forecasting model named Hierarchical Spatial-Temporal Transformer Network (HSTTN) to address the long-term WPF problems.

NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models

1 code implementation28 May 2023 Kai Mei, Zheng Li, Zhenting Wang, Yang Zhang, Shiqing Ma

Such attacks can be easily affected by retraining on downstream tasks and with different prompting strategies, limiting the transferability of backdoor attacks.

Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models

no code implementations23 May 2023 Yiting Qu, Xinyue Shen, Xinlei He, Michael Backes, Savvas Zannettou, Yang Zhang

Our evaluation result shows that 24% of the generated images using DreamBooth are hateful meme variants that present the features of the original hateful meme and the target individual/community; these generated images are comparable to hateful meme variants collected from the real world.

MetaAdapt: Domain Adaptive Few-Shot Misinformation Detection via Meta Learning

1 code implementation22 May 2023 Zhenrui Yue, Huimin Zeng, Yang Zhang, Lanyu Shang, Dong Wang

As such, MetaAdapt can learn how to adapt the misinformation detection model and exploit the source data for improved performance in the target domain.

Meta-Learning Misinformation +1

Vision-language models boost food composition compilation

no code implementations18 May 2023 Peihua Ma, Yixin Wu, Ning Yu, Yang Zhang, Michael Backes, Qin Wang, Cheng-I Wei

Nutrition information plays a pillar role in clinical dietary practice, precision nutrition, and food industry.


Two-in-One: A Model Hijacking Attack Against Text Generation Models

no code implementations12 May 2023 Wai Man Si, Michael Backes, Yang Zhang, Ahmed Salem

In this work, we broaden the scope of this attack to include text generation and classification models, hence showing its broader applicability.

Face Recognition Image Classification +7

NL2TL: Transforming Natural Languages to Temporal Logics using Large Language Models

1 code implementation12 May 2023 Yongchao Chen, Rujul Gandhi, Yang Zhang, Chuchu Fan

Then, we finetune T5 models on the lifted versions (i. e., the specific Atomic Propositions (AP) are hidden) of the NL and TL.

Is ChatGPT Fair for Recommendation? Evaluating Fairness in Large Language Model Recommendation

1 code implementation12 May 2023 Jizhi Zhang, Keqin Bao, Yang Zhang, Wenjie Wang, Fuli Feng, Xiangnan He

The remarkable achievements of Large Language Models (LLMs) have led to the emergence of a novel recommendation paradigm -- Recommendation via LLM (RecLLM).

Fairness Language Modelling

Faster OreFSDet : A Lightweight and Effective Few-shot Object Detector for Ore Images

1 code implementation2 May 2023 Yang Zhang, Le Cheng, Yuting Peng, Chengming Xu, Yanwei Fu, Bo Wu, Guodong Sun

For the ore particle size detection, obtaining a sizable amount of high-quality ore labeled data is time-consuming and expensive.

object-detection Object Detection

TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation

1 code implementation30 Apr 2023 Keqin Bao, Jizhi Zhang, Yang Zhang, Wenjie Wang, Fuli Feng, Xiangnan He

We have demonstrated that the proposed TALLRec framework can significantly enhance the recommendation capabilities of LLMs in the movie and book domains, even with a limited dataset of fewer than 100 samples.

Domain Generalization Language Modelling +1

SAM Meets Robotic Surgery: An Empirical Study in Robustness Perspective

no code implementations28 Apr 2023 An Wang, Mobarakol Islam, Mengya Xu, Yang Zhang, Hongliang Ren

In this empirical study, we investigate the robustness and zero-shot generalizability of the SAM in the domain of robotic surgery in various settings of (i) prompted vs. unprompted; (ii) bounding box vs. points-based prompt; (iii) generalization under corruptions and perturbations with five severity levels; and (iv) state-of-the-art supervised model vs. SAM.

Semantic Segmentation

Prediction then Correction: An Abductive Prediction Correction Method for Sequential Recommendation

no code implementations27 Apr 2023 Yulong Huang, Yang Zhang, Qifan Wang, Chenxu Wang, Fuli Feng

To improve the accuracy of these models, some researchers have attempted to simulate human analogical reasoning to correct predictions for testing data by drawing analogies with the prediction errors of similar training data.

Sequential Recommendation

Reformulating CTR Prediction: Learning Invariant Feature Interactions for Recommendation

1 code implementation26 Apr 2023 Yang Zhang, Tianhao Shi, Fuli Feng, Wenjie Wang, Dingxian Wang, Xiangnan He, Yongdong Zhang

However, such a manner inevitably learns unstable feature interactions, i. e., the ones that exhibit strong correlations in historical data but generalize poorly for future serving.

Click-Through Rate Prediction Disentanglement +1

In ChatGPT We Trust? Measuring and Characterizing the Reliability of ChatGPT

no code implementations18 Apr 2023 Xinyue Shen, Zeyuan Chen, Michael Backes, Yang Zhang

In this paper, we perform the first large-scale measurement of ChatGPT's reliability in the generic QA scenario with a carefully curated set of 5, 695 questions across ten datasets and eight domains.

Question Answering

Improving Neural Radiance Fields with Depth-aware Optimization for Novel View Synthesis

1 code implementation11 Apr 2023 Shu Chen, Junyao Li, Yang Zhang, Beiji Zou

Through these explicit constraints and the implicit constraint from NeRF, our method improves the view synthesis as well as the 3D-scene geometry performance of NeRF at the same time.

Depth Estimation Novel View Synthesis

Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synthesis

1 code implementation7 Apr 2023 Qiucheng Wu, Yujian Liu, Handong Zhao, Trung Bui, Zhe Lin, Yang Zhang, Shiyu Chang

We then impose spatial attention control by combining the attention over the entire text description and that over the local description of the particular object in the corresponding pixel region of that object.

Denoising Image Generation

Towards Coherent Image Inpainting Using Denoising Diffusion Implicit Models

1 code implementation6 Apr 2023 Guanhua Zhang, Jiabao Ji, Yang Zhang, Mo Yu, Tommi Jaakkola, Shiyu Chang

COPAINT also uses the Bayesian framework to jointly modify both revealed and unrevealed regions, but approximates the posterior distribution in a way that allows the errors to gradually drop to zero throughout the denoising steps, thus strongly penalizing any mismatches with the reference image.

Denoising Image Inpainting

FACE-AUDITOR: Data Auditing in Facial Recognition Systems

no code implementations5 Apr 2023 Min Chen, Zhikun Zhang, Tianhao Wang, Michael Backes, Yang Zhang

Few-shot-based facial recognition systems have gained increasing attention due to their scalability and ability to work with a few face images during the model deployment phase.

MGTBench: Benchmarking Machine-Generated Text Detection

1 code implementation26 Mar 2023 Xinlei He, Xinyue Shen, Zeyuan Chen, Michael Backes, Yang Zhang

Nonetheless, we note that only a small fraction of adversarial-crafted perturbations on MGTs can evade the ChatGPT Detector, thus highlighting the need for more robust MGT detection methods.

Benchmarking Question Answering +3

Dual Memory Aggregation Network for Event-Based Object Detection with Learnable Representation

1 code implementation17 Mar 2023 Dongsheng Wang, Xu Jia, Yang Zhang, Xinyu Zhang, Yaoyuan Wang, Ziyang Zhang, Dong Wang, Huchuan Lu

To fully exploit information with event streams to detect objects, a dual-memory aggregation network (DMANet) is proposed to leverage both long and short memory along event streams to aggregate effective information for object detection.

object-detection Object Detection

A Generative Model for Digital Camera Noise Synthesis

no code implementations16 Mar 2023 Mingyang Song, Yang Zhang, Tunç O. Aydın, Elham Amin Mansour, Christopher Schroers

To this end, we propose an effective generative model which utilizes clean features as guidance followed by noise injections into the network.

From Visual Prompt Learning to Zero-Shot Transfer: Mapping Is All You Need

no code implementations9 Mar 2023 Ziqing Yang, Zeyang Sha, Michael Backes, Yang Zhang

In this sense, we propose SeMap, a more effective mapping using the semantic alignment between the pre-trained model's knowledge and the downstream task.

A Plot is Worth a Thousand Words: Model Information Stealing Attacks via Scientific Plots

1 code implementation23 Feb 2023 Boyang Zhang, Xinlei He, Yun Shen, Tianhao Wang, Yang Zhang

Given the simplicity and effectiveness of the attack method, our study indicates scientific plots indeed constitute a valid side channel for model information stealing attacks.

Prompt Stealing Attacks Against Text-to-Image Generation Models

no code implementations20 Feb 2023 Xinyue Shen, Yiting Qu, Michael Backes, Yang Zhang

In this paper, we propose a novel attack, namely prompt stealing attack, which aims to steal prompts from generated images by text-to-image generation models.

Text-to-Image Generation

Pseudo Label-Guided Model Inversion Attack via Conditional Generative Adversarial Network

1 code implementation20 Feb 2023 Xiaojian Yuan, Kejiang Chen, Jie Zhang, Weiming Zhang, Nenghai Yu, Yang Zhang

At first, a top-n selection strategy is proposed to provide pseudo-labels for public data, and use pseudo-labels to guide the training of the cGAN.

Pseudo Label

Backdoor Attacks Against Dataset Distillation

2 code implementations3 Jan 2023 Yugeng Liu, Zheng Li, Michael Backes, Yun Shen, Yang Zhang

A model trained on this smaller distilled dataset can attain comparable performance to a model trained on the original training dataset.

Backdoor Attack

PromptBoosting: Black-Box Text Classification with Ten Forward Passes

1 code implementation19 Dec 2022 Bairu Hou, Joe O'Connor, Jacob Andreas, Shiyu Chang, Yang Zhang

Instead of directly optimizing in prompt space, PromptBoosting obtains a small pool of prompts via a gradient-free approach and then constructs a large pool of weak learners by pairing these prompts with different elements of the LM's output distribution.

Language Modelling text-classification +1

TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimization

1 code implementation19 Dec 2022 Bairu Hou, Jinghan Jia, Yihua Zhang, Guanhua Zhang, Yang Zhang, Sijia Liu, Shiyu Chang

Robustness evaluation against adversarial examples has become increasingly important to unveil the trustworthiness of the prevailing deep models in natural language processing (NLP).

Adversarial Defense Adversarial Robustness +1

Fine-Tuning Is All You Need to Mitigate Backdoor Attacks

no code implementations18 Dec 2022 Zeyang Sha, Xinlei He, Pascal Berrang, Mathias Humbert, Yang Zhang

Backdoor attacks represent one of the major threats to machine learning models.

Uncovering the Disentanglement Capability in Text-to-Image Diffusion Models

1 code implementation CVPR 2023 Qiucheng Wu, Yujian Liu, Handong Zhao, Ajinkya Kale, Trung Bui, Tong Yu, Zhe Lin, Yang Zhang, Shiyu Chang

Based on this finding, we further propose a simple, light-weight image editing algorithm where the mixing weights of the two text embeddings are optimized for style matching and content preservation.

Denoising Disentanglement

On the Evolution of (Hateful) Memes by Means of Multimodal Contrastive Learning

2 code implementations13 Dec 2022 Yiting Qu, Xinlei He, Shannon Pierson, Michael Backes, Yang Zhang, Savvas Zannettou

The dissemination of hateful memes online has adverse effects on social media platforms and the real world.

Contrastive Learning

Detection of brain activations induced by naturalistic stimuli in a pseudo model-driven way

no code implementations3 Dec 2022 Jiangcong Liu, Hao Ma, Yun Guan, Fan Wu, Le Xu, Yang Zhang, Lixia Tian

We evaluated the effectiveness of AINS with both statistical and predictive analyses on individual differences in sex and intelligence quotient (IQ), based on the four movie fMRI runs included in the Human Connectome Project dataset.

Visual Fault Detection of Multi-scale Key Components in Freight Trains

no code implementations26 Nov 2022 Yang Zhang, Yang Zhou, Huilin Pan, Bo Wu, Guodong Sun

Fault detection for key components in the braking system of freight trains is critical for ensuring railway transportation safety.

Fault Detection

BiFSMNv2: Pushing Binary Neural Networks for Keyword Spotting to Real-Network Performance

1 code implementation13 Nov 2022 Haotong Qin, Xudong Ma, Yifu Ding, Xiaoyang Li, Yang Zhang, Zejun Ma, Jiakai Wang, Jie Luo, Xianglong Liu

We highlight that benefiting from the compact architecture and optimized hardware kernel, BiFSMNv2 can achieve an impressive 25. 1x speedup and 20. 2x storage-saving on edge hardware.

Binarization Keyword Spotting

Learning to Learn Domain-invariant Parameters for Domain Generalization

no code implementations4 Nov 2022 Feng Hou, Yao Zhang, Yang Liu, Jin Yuan, Cheng Zhong, Yang Zhang, Zhongchao shi, Jianping Fan, Zhiqiang He

Due to domain shift, deep neural networks (DNNs) usually fail to generalize well on unknown test data in practice.

Domain Generalization

SAP-DETR: Bridging the Gap Between Salient Points and Queries-Based Transformer Detector for Fast Model Convergency

1 code implementation CVPR 2023 Yang Liu, Yao Zhang, Yixin Wang, Yang Zhang, Jiang Tian, Zhongchao shi, Jianping Fan, Zhiqiang He

To bridge the gap between the reference points of salient queries and Transformer detectors, we propose SAlient Point-based DETR (SAP-DETR) by treating object detection as a transformation from salient points to instance objects.

object-detection Object Detection

Amplifying Membership Exposure via Data Poisoning

1 code implementation1 Nov 2022 Yufei Chen, Chao Shen, Yun Shen, Cong Wang, Yang Zhang

In this paper, we investigate the third type of exploitation of data poisoning - increasing the risks of privacy leakage of benign training samples.

Data Poisoning Overall - Test +1

DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Generation Models

no code implementations13 Oct 2022 Zeyang Sha, Zheng Li, Ning Yu, Yang Zhang

To tackle this problem, we pioneer a systematic study on the detection and attribution of fake images generated by text-to-image generation models.

Fake Image Detection Text-to-Image Generation

Unsupervised Domain Adaptation for COVID-19 Information Service with Contrastive Adversarial Domain Mixup

no code implementations6 Oct 2022 Huimin Zeng, Zhenrui Yue, Ziyi Kou, Lanyu Shang, Yang Zhang, Dong Wang

Moreover, we leverage the power of domain adversarial examples to establish an intermediate domain mixup, where the latent representations of the input text from both domains could be mixed during the training process.

Contrastive Learning Misinformation +1

Backdoor Attacks in the Supply Chain of Masked Image Modeling

no code implementations4 Oct 2022 Xinyue Shen, Xinlei He, Zheng Li, Yun Shen, Michael Backes, Yang Zhang

Different from previous work, we are the first to systematically threat modeling on SSL in every phase of the model supply chain, i. e., pre-training, release, and downstream phases.

Contrastive Learning Self-Supervised Learning

UnGANable: Defending Against GAN-based Face Manipulation

1 code implementation3 Oct 2022 Zheng Li, Ning Yu, Ahmed Salem, Michael Backes, Mario Fritz, Yang Zhang

Extensive experiments on four popular GAN models trained on two benchmark face datasets show that UnGANable achieves remarkable effectiveness and utility performance, and outperforms multiple baseline methods.

Face Swapping Misinformation

Membership Inference Attacks Against Text-to-image Generation Models

no code implementations3 Oct 2022 Yixin Wu, Ning Yu, Zheng Li, Michael Backes, Yang Zhang

The empirical results show that all of the proposed attacks can achieve significant performance, in some cases even close to an accuracy of 1, and thus the corresponding risk is much more severe than that shown by existing membership inference attacks.

Image Classification Text-to-Image Generation

On Attacking Out-Domain Uncertainty Estimation in Deep Neural Networks

no code implementations3 Oct 2022 Huimin Zeng, Zhenrui Yue, Yang Zhang, Ziyi Kou, Lanyu Shang, Dong Wang

In many applications with real-world consequences, it is crucial to develop reliable uncertainty estimation for the predictions made by the AI decision systems.

Adversarial Attack

Structure-Aware NeRF without Posed Camera via Epipolar Constraint

1 code implementation1 Oct 2022 Shu Chen, Yang Zhang, Yaxin Xu, Beiji Zou

This two-stage strategy is not convenient to use and degrades the performance because the error in the pose extraction can propagate to the view synthesis.

Novel View Synthesis

Data Poisoning Attacks Against Multimodal Encoders

1 code implementation30 Sep 2022 Ziqing Yang, Xinlei He, Zheng Li, Michael Backes, Mathias Humbert, Pascal Berrang, Yang Zhang

Extensive evaluations on different datasets and model architectures show that all three attacks can achieve significant attack performance while maintaining model utility in both visual and linguistic modalities.

Contrastive Learning Data Poisoning

Rethinking Missing Data: Aleatoric Uncertainty-Aware Recommendation

no code implementations22 Sep 2022 Chenxu Wang, Fuli Feng, Yang Zhang, Qifan Wang, Xunhan Hu, Xiangnan He

A standard choice is treating the missing data as negative training samples and estimating interaction likelihood between user-item pairs along with the observed interactions.

Fairness Reprogramming

1 code implementation21 Sep 2022 Guanhua Zhang, Yihua Zhang, Yang Zhang, Wenqi Fan, Qing Li, Sijia Liu, Shiyu Chang

Specifically, FairReprogram considers the case where models can not be changed and appends to the input a set of perturbations, called the fairness trigger, which is tuned towards the fairness criteria under a min-max formulation.


Predicting Protein-Ligand Binding Affinity via Joint Global-Local Interaction Modeling

no code implementations18 Sep 2022 Yang Zhang, Gengmo Zhou, Zhewei Wei, Hongteng Xu

The prediction of protein-ligand binding affinity is of great significance for discovering lead compounds in drug research.

On the Privacy Risks of Cell-Based NAS Architectures

1 code implementation4 Sep 2022 Hai Huang, Zhikun Zhang, Yun Shen, Michael Backes, Qi Li, Yang Zhang

Existing studies on neural architecture search (NAS) mainly focus on efficiently and effectively searching for network architectures with better performance.

Neural Architecture Search

Membership Inference Attacks by Exploiting Loss Trajectory

1 code implementation31 Aug 2022 Yiyong Liu, Zhengyu Zhao, Michael Backes, Yang Zhang

Machine learning models are vulnerable to membership inference attacks in which an adversary aims to predict whether or not a particular sample was contained in the target model's training dataset.

Knowledge Distillation

Auditing Membership Leakages of Multi-Exit Networks

no code implementations23 Aug 2022 Zheng Li, Yiyong Liu, Xinlei He, Ning Yu, Michael Backes, Yang Zhang

Furthermore, we propose a hybrid attack that exploits the exit information to improve the performance of existing attacks.

Membership-Doctor: Comprehensive Assessment of Membership Inference Against Machine Learning Models

no code implementations22 Aug 2022 Xinlei He, Zheng Li, Weilin Xu, Cory Cornelius, Yang Zhang

Finally, we find that data augmentation degrades the performance of existing attacks to a larger extent, and we propose an adaptive attack using augmentation to train shadow and attack models that improve attack performance.

Data Augmentation

AI for Global Climate Cooperation: Modeling Global Climate Negotiations, Agreements, and Long-Term Cooperation in RICE-N

1 code implementation15 Aug 2022 Tianyu Zhang, Andrew Williams, Soham Phade, Sunil Srinivasa, Yang Zhang, Prateek Gupta, Yoshua Bengio, Stephan Zheng

To facilitate this research, here we introduce RICE-N, a multi-region integrated assessment model that simulates the global climate and economy, and which can be used to design and evaluate the strategic outcomes for different negotiation and agreement frameworks.

Ethics Multi-agent Reinforcement Learning

Semi-Leak: Membership Inference Attacks Against Semi-supervised Learning

1 code implementation25 Jul 2022 Xinlei He, Hongbin Liu, Neil Zhenqiang Gong, Yang Zhang

The results show that early stopping can mitigate the membership inference attack, but with the cost of model's utility degradation.

Data Augmentation Inference Attack +1

Tackling Spoofing-Aware Speaker Verification with Multi-Model Fusion

no code implementations18 Jun 2022 Haibin Wu, Jiawen Kang, Lingwei Meng, Yang Zhang, Xixin Wu, Zhiyong Wu, Hung-Yi Lee, Helen Meng

However, previous works show that state-of-the-art ASV models are seriously vulnerable to voice spoofing attacks, and the recently proposed high-performance spoofing countermeasure (CM) models only focus solely on the standalone anti-spoofing tasks, and ignore the subsequent speaker verification process.

Speaker Verification

Data-Efficient Double-Win Lottery Tickets from Robust Pre-training

1 code implementation9 Jun 2022 Tianlong Chen, Zhenyu Zhang, Sijia Liu, Yang Zhang, Shiyu Chang, Zhangyang Wang

For example, on downstream CIFAR-10/100 datasets, we identify double-win matching subnetworks with the standard, fast adversarial, and adversarial pre-training from ImageNet, at 89. 26%/73. 79%, 89. 26%/79. 03%, and 91. 41%/83. 22% sparsity, respectively.

Transfer Learning

mmFormer: Multimodal Medical Transformer for Incomplete Multimodal Learning of Brain Tumor Segmentation

1 code implementation6 Jun 2022 Yao Zhang, Nanjun He, Jiawei Yang, Yuexiang Li, Dong Wei, Yawen Huang, Yang Zhang, Zhiqiang He, Yefeng Zheng

Concretely, we propose a novel multimodal Medical Transformer (mmFormer) for incomplete multimodal learning with three main components: the hybrid modality-specific encoders that bridge a convolutional encoder and an intra-modal Transformer for both local and global context modeling within each modality; an inter-modal Transformer to build and align the long-range correlations across modalities for modality-invariant features with global semantics corresponding to tumor region; a decoder that performs a progressive up-sampling and fusion with the modality-invariant features to generate robust segmentation.

Brain Tumor Segmentation Tumor Segmentation

Decoupled Pyramid Correlation Network for Liver Tumor Segmentation from CT images

no code implementations26 May 2022 Yao Zhang, Jiawei Yang, Yang Liu, Jiang Tian, Siyun Wang, Cheng Zhong, Zhongchao shi, Yang Zhang, Zhiqiang He

In this paper, we propose a Decoupled Pyramid Correlation Network (DPC-Net) that exploits attention mechanisms to fully leverage both low- and high-level features embedded in FCN to segment liver tumor.

Computed Tomography (CT) Image Segmentation +2

A Lightweight NMS-free Framework for Real-time Visual Fault Detection System of Freight Trains

no code implementations25 May 2022 Guodong Sun, Yang Zhou, Huilin Pan, Bo Wu, Ye Hu, Yang Zhang

In this paper, we propose a lightweight NMS-free framework to achieve real-time detection and high accuracy simultaneously.

Fault Detection

Mitigating Hidden Confounding Effects for Causal Recommendation

no code implementations16 May 2022 Xinyuan Zhu, Yang Zhang, Fuli Feng, Xun Yang, Dingxian Wang, Xiangnan He

Towards this goal, we propose a Hidden Confounder Removal (HCR) framework that leverages front-door adjustment to decompose the causal effect into two partial effects, according to the mediators between item features and user feedback.

Multi-Task Learning Recommendation Systems

Addressing Confounding Feature Issue for Causal Recommendation

1 code implementation13 May 2022 Xiangnan He, Yang Zhang, Fuli Feng, Chonggang Song, Lingling Yi, Guohui Ling, Yongdong Zhang

We demonstrate DCR on the backbone model of neural factorization machine (NFM), showing that DCR leads to more accurate prediction of user preference with small inference time cost.

Recommendation Systems

FairSR: Fairness-aware Sequential Recommendation through Multi-Task Learning with Preference Graph Embeddings

no code implementations30 Apr 2022 Cheng-Te Li, Cheng Hsu, Yang Zhang

We propose a novel fairness-aware sequential recommendation task, in which a new metric, interaction fairness, is defined to estimate how recommended items are fairly interacted by users with different protected attribute groups.

Fairness Graph Embedding +2

ContentVec: An Improved Self-Supervised Speech Representation by Disentangling Speakers

1 code implementation20 Apr 2022 Kaizhi Qian, Yang Zhang, Heting Gao, Junrui Ni, Cheng-I Lai, David Cox, Mark Hasegawa-Johnson, Shiyu Chang

Self-supervised learning in speech involves training a speech representation network on a large-scale unannotated speech corpus, and then applying the learned representations to downstream tasks.

Disentanglement Self-Supervised Learning

Finding MNEMON: Reviving Memories of Node Embeddings

no code implementations14 Apr 2022 Yun Shen, Yufei Han, Zhikun Zhang, Min Chen, Ting Yu, Michael Backes, Yang Zhang, Gianluca Stringhini

Previous security research efforts orbiting around graphs have been exclusively focusing on either (de-)anonymizing the graphs or understanding the security and privacy issues of graph neural networks.

Graph Embedding

Analyzing the Effects of Handling Data Imbalance on Learned Features from Medical Images by Looking Into the Models

no code implementations4 Apr 2022 Ashkan Khakzar, Yawei Li, Yang Zhang, Mirac Sanisoglu, Seong Tae Kim, Mina Rezaei, Bernd Bischl, Nassir Navab

One challenging property lurking in medical datasets is the imbalanced data distribution, where the frequency of the samples between the different classes is not balanced.

Unsupervised Text-to-Speech Synthesis by Unsupervised Automatic Speech Recognition

1 code implementation29 Mar 2022 Junrui Ni, Liming Wang, Heting Gao, Kaizhi Qian, Yang Zhang, Shiyu Chang, Mark Hasegawa-Johnson

An unsupervised text-to-speech synthesis (TTS) system learns to generate speech waveforms corresponding to any written sentence in a language by observing: 1) a collection of untranscribed speech waveforms in that language; 2) a collection of texts written in that language without access to any transcribed speech.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Shallow Fusion of Weighted Finite-State Transducer and Language Model for Text Normalization

1 code implementation29 Mar 2022 Evelina Bakhturina, Yang Zhang, Boris Ginsburg

First, a non-deterministic WFST outputs all normalization candidates, and then a neural language model picks the best one -- similar to shallow fusion for automatic speech recognition.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

SpeechSplit 2.0: Unsupervised speech disentanglement for voice conversion Without tuning autoencoder Bottlenecks

1 code implementation26 Mar 2022 Chak Ho Chan, Kaizhi Qian, Yang Zhang, Mark Hasegawa-Johnson

SpeechSplit can perform aspect-specific voice conversion by disentangling speech into content, rhythm, pitch, and timbre using multiple autoencoders in an unsupervised manner.

Disentanglement Voice Conversion

Linking Emergent and Natural Languages via Corpus Transfer

1 code implementation ICLR 2022 Shunyu Yao, Mo Yu, Yang Zhang, Karthik R Narasimhan, Joshua B. Tenenbaum, Chuang Gan

In this work, we propose a novel way to establish such a link by corpus transfer, i. e. pretraining on a corpus of emergent language for downstream natural language tasks, which is in contrast to prior work that directly transfers speaker and listener parameters.

Disentanglement Image Captioning +1

Adversarial Support Alignment

1 code implementation ICLR 2022 Shangyuan Tong, Timur Garipov, Yang Zhang, Shiyu Chang, Tommi S. Jaakkola

Furthermore, we show that our approach can be viewed as a limit of existing notions of alignment by increasing transportation assignment tolerance.

Domain Adaptation

BiFSMN: Binary Neural Network for Keyword Spotting

1 code implementation14 Feb 2022 Haotong Qin, Xudong Ma, Yifu Ding, Xiaoyang Li, Yang Zhang, Yao Tian, Zejun Ma, Jie Luo, Xianglong Liu

Then, to allow the instant and adaptive accuracy-efficiency trade-offs at runtime, we also propose a Thinnable Binarization Architecture to further liberate the acceleration potential of the binarized network from the topology perspective.

Binarization Keyword Spotting

Topogivity: A Machine-Learned Chemical Rule for Discovering Topological Materials

1 code implementation10 Feb 2022 Andrew Ma, Yang Zhang, Thomas Christensen, Hoi Chun Po, Li Jing, Liang Fu, Marin Soljačić

Topological materials present unconventional electronic properties that make them attractive for both basic science and next-generation technological applications.

SSLGuard: A Watermarking Scheme for Self-supervised Learning Pre-trained Encoders

1 code implementation27 Jan 2022 Tianshuo Cong, Xinlei He, Yang Zhang

Recent research has shown that the machine learning model's copyright is threatened by model stealing attacks, which aim to train a surrogate model to mimic the behavior of a given model.

Self-Supervised Learning

Towards Realistic Visual Dubbing with Heterogeneous Sources

no code implementations17 Jan 2022 Tianyi Xie, Liucheng Liao, Cheng Bi, Benlai Tang, Xiang Yin, Jianfei Yang, Mingjie Wang, Jiali Yao, Yang Zhang, Zejun Ma

The task of few-shot visual dubbing focuses on synchronizing the lip movements with arbitrary speech input for any talking head video.

Disentanglement Talking Head Generation

Attention-based Dual Supervised Decoder for RGBD Semantic Segmentation

1 code implementation5 Jan 2022 Yang Zhang, Yang Yang, Chenyun Xiong, Guodong Sun, Yanwen Guo

Encoder-decoder models have been widely used in RGBD semantic segmentation, and most of them are designed via a two-stream network.

RGBD Semantic Segmentation Semantic Segmentation

Model Stealing Attacks Against Inductive Graph Neural Networks

1 code implementation15 Dec 2021 Yun Shen, Xinlei He, Yufei Han, Yang Zhang

Graph neural networks (GNNs), a new family of machine learning (ML) models, have been proposed to fully leverage graph data to build powerful applications.

Recommending Multiple Positive Citations for Manuscript via Content-Dependent Modeling and Multi-Positive Triplet

no code implementations25 Nov 2021 Yang Zhang, Qiang Ma

Third, we propose a dynamic context sampling strategy which captures the ``macro-scoped'' citing intents from a manuscript and empowers the citation embeddings to be content-dependent, which allow the algorithm to further improve the performances.

Citation Recommendation

Incentive Mechanisms for Federated Learning: From Economic and Game Theoretic Perspective

no code implementations20 Nov 2021 Xuezhen Tu, Kun Zhu, Nguyen Cong Luong, Dusit Niyato, Yang Zhang, Juan Li

In this paper, we provide a comprehensive review for the economic and game theoretic approaches proposed in the literature to design various schemes for stimulating data owners to participate in FL training process.

Federated Learning

Property Inference Attacks Against GANs

1 code implementation15 Nov 2021 Junhao Zhou, Yufei Chen, Chao Shen, Yang Zhang

In addition, we show that our attacks can be used to enhance the performance of membership inference against GANs.

Fairness Inference Attack

A Survey of Visual Transformers

1 code implementation11 Nov 2021 Yang Liu, Yao Zhang, Yixin Wang, Feng Hou, Jin Yuan, Jiang Tian, Yang Zhang, Zhongchao shi, Jianping Fan, Zhiqiang He

Transformer, an attention-based encoder-decoder model, has already revolutionized the field of natural language processing (NLP).

Get a Model! Model Hijacking Attack Against Machine Learning Models

no code implementations8 Nov 2021 Ahmed Salem, Michael Backes, Yang Zhang

In this work, we propose a new training time attack against computer vision based machine learning models, namely model hijacking attack.

Autonomous Driving BIG-bench Machine Learning +1

LF-YOLO: A Lighter and Faster YOLO for Weld Defect Detection of X-ray Image

1 code implementation28 Oct 2021 Moyun Liu, Youping Chen, Lei He, Yang Zhang, Jingming Xie

To further prove the ability of our method, we test it on public dataset MS COCO, and the results show that our LF-YOLO has a outstanding versatility detection performance.

Defect Detection

Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networks

1 code implementation NeurIPS 2021 Yonggan Fu, Qixuan Yu, Yang Zhang, Shang Wu, Xu Ouyang, David Cox, Yingyan Lin

Deep Neural Networks (DNNs) are known to be vulnerable to adversarial attacks, i. e., an imperceptible perturbation to the input can mislead DNNs trained on clean images into making erroneous predictions.

Adversarial Robustness

Understanding Interlocking Dynamics of Cooperative Rationalization

1 code implementation NeurIPS 2021 Mo Yu, Yang Zhang, Shiyu Chang, Tommi S. Jaakkola

The selection mechanism is commonly integrated into the model itself by specifying a two-component cascaded system consisting of a rationale generator, which makes a binary selection of the input features (which is the rationale), and a predictor, which predicts the output based only on the selected features.

Hard Attention

Adaptive Fusion Affinity Graph with Noise-free Online Low-rank Representation for Natural Image Segmentation

1 code implementation22 Oct 2021 Yang Zhang, Moyun Liu, Huiming Zhang, Guodong Sun, Jingwu He

To reduce time complexity while improving performance, a sparse representation of global nodes based on noise-free online low-rank representation is used to obtain a global graph at each scale.

Density Estimation Image Segmentation +2

A Lightweight and Accurate Recognition Framework for Signs of X-ray Weld Images

no code implementations18 Oct 2021 Moyun Liu, Jingming Xie, Jing Hao, Yang Zhang, Xuzhan Chen, Youping Chen

Based on SCE module, a narrow network is designed for final weld information recognition.

Exploring Timbre Disentanglement in Non-Autoregressive Cross-Lingual Text-to-Speech

no code implementations14 Oct 2021 Haoyue Zhan, Xinyuan Yu, Haitong Zhang, Yang Zhang, Yue Lin

In this paper, we study the disentanglement of speaker and language representations in non-autoregressive cross-lingual TTS models from various aspects.

Disentanglement Voice Cloning

Revisiting IPA-based Cross-lingual Text-to-speech

no code implementations14 Oct 2021 Haitong Zhang, Haoyue Zhan, Yang Zhang, Xinyuan Yu, Yue Lin

Experiments show that the way to process the IPA and suprasegmental sequence has a negligible impact on the CL VC performance.

Voice Cloning

Inference Attacks Against Graph Neural Networks

1 code implementation6 Oct 2021 Zhikun Zhang, Min Chen, Michael Backes, Yun Shen, Yang Zhang

Second, given a subgraph of interest and the graph embedding, we can determine with high confidence that whether the subgraph is contained in the target graph.

Graph Classification Graph Embedding +1

Membership Inference Attacks Against Recommender Systems

1 code implementation16 Sep 2021 Minxing Zhang, Zhaochun Ren, Zihan Wang, Pengjie Ren, Zhumin Chen, Pengfei Hu, Yang Zhang

In this paper, we make the first attempt on quantifying the privacy leakage of recommender systems through the lens of membership inference.

Recommendation Systems

Effective Tensor Completion via Element-wise Weighted Low-rank Tensor Train with Overlapping Ket Augmentation

1 code implementation13 Sep 2021 Yang Zhang, Yao Wang, Zhi Han, Xi'ai Chen, Yandong Tang

Accordingly, a novel formulation for tensor completion and an effective optimization algorithm, called as tensor completion by parallel weighted matrix factorization via tensor train (TWMac-TT), is proposed.

A Unified Transformer-based Framework for Duplex Text Normalization

no code implementations23 Aug 2021 Tuan Manh Lai, Yang Zhang, Evelina Bakhturina, Boris Ginsburg, Heng Ji

In addition, we also create a cleaned dataset from the Spoken Wikipedia Corpora for German and report the performance of our systems on the dataset.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +4

Deep Sequence Modeling: Development and Applications in Asset Pricing

no code implementations20 Aug 2021 Lin William Cong, Ke Tang, Jingyuan Wang, Yang Zhang

We predict asset returns and measure risk premia using a prominent technique from artificial intelligence -- deep sequence modeling.

Time Series Analysis

Pro-UIGAN: Progressive Face Hallucination from Occluded Thumbnails

no code implementations2 Aug 2021 Yang Zhang, Xin Yu, Xiaobo Lu, Ping Liu

Specifically, we design a novel cross-modal transformer module for facial priors estimation, in which an input face and its landmark features are formulated as queries and keys, respectively.

Face Alignment Face Hallucination +2

TumorCP: A Simple but Effective Object-Level Data Augmentation for Tumor Segmentation

1 code implementation21 Jul 2021 Jiawei Yang, Yao Zhang, Yuan Liang, Yang Zhang, Lei He, Zhiqiang He

Experiments on kidney tumor segmentation task demonstrate that TumorCP surpasses the strong baseline by a remarkable margin of 7. 12% on tumor Dice.

Data Augmentation Tumor Segmentation

Modality-aware Mutual Learning for Multi-modal Medical Image Segmentation

2 code implementations21 Jul 2021 Yao Zhang, Jiawei Yang, Jiang Tian, Zhongchao shi, Cheng Zhong, Yang Zhang, Zhiqiang He

To this end, we propose a novel mutual learning (ML) strategy for effective and robust multi-modal liver tumor segmentation.

Computed Tomography (CT) Image Segmentation +2

Tea: Program Repair Using Neural Network Based on Program Information Attention Matrix

no code implementations17 Jul 2021 Wenshuo Wang, Chen Wu, Liang Cheng, Yang Zhang

The advance in machine learning (ML)-driven natural language process (NLP) points a promising direction for automatic bug fixing for software programs, as fixing a buggy program can be transformed to a translation task.

Program Repair Translation

Leveraging Domain Agnostic and Specific Knowledge for Acronym Disambiguation

no code implementations1 Jul 2021 Qiwei Zhong, Guanxiong Zeng, Danqing Zhu, Yang Zhang, Wangli Lin, Ben Chen, Jiayu Tang

In this paper, we consider both the domain agnostic and specific knowledge, and propose a Hierarchical Dual-path BERT method coined hdBERT to capture the general fine-grained and high-level specific representations for acronym disambiguation.

Word Embeddings

ACN: Adversarial Co-training Network for Brain Tumor Segmentation with Missing Modalities

2 code implementations28 Jun 2021 Yixin Wang, Yang Zhang, Yang Liu, Zihao Lin, Jiang Tian, Cheng Zhong, Zhongchao shi, Jianping Fan, Zhiqiang He

Specifically, ACN adopts a novel co-training network, which enables a coupled learning process for both full modality and missing modality to supplement each other's domain and feature representations, and more importantly, to recover the `missing' information of absent modalities.

Brain Tumor Segmentation Transfer Learning +1

Teacher Model Fingerprinting Attacks Against Transfer Learning

2 code implementations23 Jun 2021 Yufei Chen, Chao Shen, Cong Wang, Yang Zhang

To this end, we propose a teacher model fingerprinting attack to infer the origin of a student model, i. e., the teacher model it transfers from.

Transfer Learning

AOMD: An Analogy-aware Approach to Offensive Meme Detection on Social Media

no code implementations21 Jun 2021 Lanyu Shang, Yang Zhang, Yuheng Zha, Yingxi Chen, Christina Youn, Dong Wang

To address the above challenges, we develop a deep learning based Analogy-aware Offensive Meme Detection (AOMD) framework to learn the implicit analogy from the multi-modal contents of the meme and effectively detect offensive analogy memes.

Trust It or Not: Confidence-Guided Automatic Radiology Report Generation

no code implementations21 Jun 2021 Yixin Wang, Zihao Lin, Zhe Xu, Haoyu Dong, Jiang Tian, Jie Luo, Zhongchao shi, Yang Zhang, Jianping Fan, Zhiqiang He

Experimental results have demonstrated that the proposed method for model uncertainty characterization and estimation can produce more reliable confidence scores for radiology report generation, and the modified loss function, which takes into account the uncertainties, leads to better model performance on two public radiology report datasets.

Decision Making Image Captioning +1

BadNL: Backdoor Attacks Against NLP Models

no code implementations ICML Workshop AML 2021 Xiaoyi Chen, Ahmed Salem, Michael Backes, Shiqing Ma, Yang Zhang

For instance, using the Word-level triggers, our backdoor attack achieves a 100% attack success rate with only a utility drop of 0. 18%, 1. 26%, and 0. 19% on three benchmark sentiment analysis datasets.

Backdoor Attack Sentiment Analysis

Multi-stage malaria parasite recognition by deep learning

1 code implementation GigaScience 2021 Sen Li, Zeyu Du, Xiangjie Meng, Yang Zhang

The proposed method showed higher accuracy and effectiveness in publicly available microscopic images of multi-stage malaria parasites compared to a wide range of state-of-the-art approaches.

Global Rhythm Style Transfer Without Text Transcriptions

1 code implementation16 Jun 2021 Kaizhi Qian, Yang Zhang, Shiyu Chang, JinJun Xiong, Chuang Gan, David Cox, Mark Hasegawa-Johnson

In this paper, we propose AutoPST, which can disentangle global prosody style from speech without relying on any text transcriptions.

Representation Learning Style Transfer

Voting for the right answer: Adversarial defense for speaker verification

1 code implementation15 Jun 2021 Haibin Wu, Yang Zhang, Zhiyong Wu, Dong Wang, Hung-Yi Lee

Automatic speaker verification (ASV) is a well developed technology for biometric identification, and has been ubiquitous implemented in security-critic applications, such as banking and access control.

Adversarial Defense Speaker Verification

Distributed Urban Freeway Traffic Optimization Considering Congestion Propagation

no code implementations11 Jun 2021 Fengkun Gao, Bo Yang, Cailian Chen, Xinping Guan, Yang Zhang

Most exiting works develop traffic optimization strategies depending on the local traffic states of congested road segments, where the congestion propagation is neglected.

Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators

1 code implementation11 Jun 2021 Yonggan Fu, Yongan Zhang, Yang Zhang, David Cox, Yingyan Lin

The key challenges include (1) the dilemma of whether to explode the memory consumption due to the huge joint space or achieve sub-optimal designs, (2) the discrete nature of the accelerator design space that is coupled yet different from that of the networks and bitwidths, and (3) the chicken and egg problem associated with network-accelerator co-search, i. e., co-search requires operation-wise hardware cost, which is lacking during search as the optimal accelerator depending on the whole network is still unknown during search.

Conversational Question Answering: A Survey

no code implementations2 Jun 2021 Munazza Zaib, Wei Emma Zhang, Quan Z. Sheng, Adnan Mahmood, Yang Zhang

Question answering (QA) systems provide a way of querying the information available in various formats including, but not limited to, unstructured and structured data in natural languages.

Conversational Question Answering

A Multi-Branch Hybrid Transformer Networkfor Corneal Endothelial Cell Segmentation

no code implementations21 May 2021 Yinglin Zhang, Risa Higashita, Huazhu Fu, Yanwu Xu, Yang Zhang, Haofeng Liu, Jian Zhang, Jiang Liu

Corneal endothelial cell segmentation plays a vital role inquantifying clinical indicators such as cell density, coefficient of variation, and hexagonality.

Cell Segmentation

SGD-QA: Fast Schema-Guided Dialogue State Tracking for Unseen Services

no code implementations17 May 2021 Yang Zhang, Vahid Noroozi, Evelina Bakhturina, Boris Ginsburg

In this paper, we propose SGD-QA, a simple and extensible model for schema-guided dialogue state tracking based on a question answering approach.

Dialogue State Tracking Goal-Oriented Dialogue Systems +1

Causal Intervention for Leveraging Popularity Bias in Recommendation

1 code implementation13 May 2021 Yang Zhang, Fuli Feng, Xiangnan He, Tianxin Wei, Chonggang Song, Guohui Ling, Yongdong Zhang

This work studies an unexplored problem in recommendation -- how to leverage popularity bias to improve the recommendation accuracy.

Collaborative Filtering Recommendation Systems

NeMo Inverse Text Normalization: From Development To Production

1 code implementation11 Apr 2021 Yang Zhang, Evelina Bakhturina, Kyle Gorman, Boris Ginsburg

Inverse text normalization (ITN) converts spoken-domain automatic speech recognition (ASR) output into written-domain text to improve the readability of the ASR output.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Hi-Fi Multi-Speaker English TTS Dataset

no code implementations3 Apr 2021 Evelina Bakhturina, Vitaly Lavrukhin, Boris Ginsburg, Yang Zhang

This paper introduces a new multi-speaker English dataset for training text-to-speech models.

Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentation

2 code implementations CVPR 2021 Zixiang Zhou, Yang Zhang, Hassan Foroosh

Panoptic segmentation presents a new challenge in exploiting the merits of both detection and segmentation, with the aim of unifying instance segmentation and semantic segmentation in a single framework.

Instance Segmentation Panoptic Segmentation

Graph Unlearning

1 code implementation27 Mar 2021 Min Chen, Zhikun Zhang, Tianhao Wang, Michael Backes, Mathias Humbert, Yang Zhang

In this paper, we propose GraphEraser, a novel machine unlearning framework tailored to graph data.

Node-Level Membership Inference Attacks Against Graph Neural Networks

no code implementations10 Feb 2021 Xinlei He, Rui Wen, Yixin Wu, Michael Backes, Yun Shen, Yang Zhang

To fully utilize the information contained in graph data, a new family of machine learning (ML) models, namely graph neural networks (GNNs), has been introduced.

BIG-bench Machine Learning

Quantifying and Mitigating Privacy Risks of Contrastive Learning

1 code implementation8 Feb 2021 Xinlei He, Yang Zhang

Our experimental results show that contrastive models trained on image datasets are less vulnerable to membership inference attacks but more vulnerable to attribute inference attacks compared to supervised models.

BIG-bench Machine Learning Contrastive Learning +3

ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models

1 code implementation4 Feb 2021 Yugeng Liu, Rui Wen, Xinlei He, Ahmed Salem, Zhikun Zhang, Michael Backes, Emiliano De Cristofaro, Mario Fritz, Yang Zhang

As a result, we lack a comprehensive picture of the risks caused by the attacks, e. g., the different scenarios they can be applied to, the common factors that influence their performance, the relationship among them, or the effectiveness of possible defenses.

BIG-bench Machine Learning Inference Attack +2

A Unified Light Framework for Real-time Fault Detection of Freight Train Images

no code implementations31 Jan 2021 Yang Zhang, Moyun Liu, Yang Yang, Yanwen Guo, Huiming Zhang

Real-time fault detection for freight trains plays a vital role in guaranteeing the security and optimal operation of railway transportation under stringent resource requirements.

Fault Detection Region Proposal

AT-BERT: Adversarial Training BERT for Acronym Identification Winning Solution for SDU@AAAI-21

no code implementations11 Jan 2021 Danqing Zhu, Wangli Lin, Yang Zhang, Qiwei Zhong, Guanxiong Zeng, Weilin Wu, Jiayu Tang

In this paper, we present an Adversarial Training BERT method named AT-BERT, our winning solution to acronym identification task for Scientific Document Understanding (SDU) Challenge of AAAI 2021.

Unsupervised Pre-training

SACoD: Sensor Algorithm Co-Design Towards Efficient CNN-powered Intelligent PhlatCam

1 code implementation ICCV 2021 Yonggan Fu, Yang Zhang, Yue Wang, Zhihan Lu, Vivek Boominathan, Ashok Veeraraghavan, Yingyan Lin

PhlatCam, with its form factor potentially reduced by orders of magnitude, has emerged as a promising solution to the first aforementioned challenge, while the second one remains a bottleneck.

Benchmarking Model Compression +1

A General Recurrent Tracking Framework Without Real Data

no code implementations ICCV 2021 Shuai Wang, Hao Sheng, Yang Zhang, Yubin Wu, Zhang Xiong

Based on this framework, a Recurrent Tracking Unit (RTU) is designed to score potential tracks through long-term information.

Multi-Object Tracking

Dynamic Backdoor Attacks Against Deep Neural Networks

no code implementations1 Jan 2021 Ahmed Salem, Rui Wen, Michael Backes, Shiqing Ma, Yang Zhang

In particular, BaN and c-BaN based on a novel generative network are the first two schemes that algorithmically generate triggers.

Unified Mandarin TTS Front-end Based on Distilled BERT Model

no code implementations31 Dec 2020 Yang Zhang, Liqun Deng, Yasheng Wang

The front-end module in a typical Mandarin text-to-speech system (TTS) is composed of a long pipeline of text processing components, which requires extensive efforts to build and is prone to large accumulative model size and cascade errors.

Knowledge Distillation Language Modelling +1

Semi-supervised Cardiac Image Segmentation via Label Propagation and Style Transfer

1 code implementation29 Dec 2020 Yao Zhang, Jiawei Yang, Feng Hou, Yang Liu, Yixin Wang, Jiang Tian, Cheng Zhong, Yang Zhang, Zhiqiang He

Accurate segmentation of cardiac structures can assist doctors to diagnose diseases, and to improve treatment planning, which is highly demanded in the clinical practice.

Image Segmentation Semantic Segmentation +1

Peierls transition, ferroelectricity, and spin-singlet formation in the monolayer VOI$_2$

no code implementations24 Dec 2020 Yang Zhang, Ling-Fang Lin, Adriana Moreo, Gonzalo Alvarez, Elbio Dagotto

Our phonon calculations indicate that the orthorhombic $Pmm2$ FE-II phase is the most likely ground state, involving a ferroelectric distortion along the $a$-axis and V-V dimerization along the $b$-axis.

Strongly Correlated Electrons

Mention Extraction and Linking for SQL Query Generation

no code implementations EMNLP 2020 Jianqiang Ma, Zeyu Yan, Shuai Pang, Yang Zhang, Jianping Shen

On the WikiSQL benchmark, state-of-the-art text-to-SQL systems typically take a slot-filling approach by building several dedicated models for each type of slots.

slot-filling Slot Filling +1

The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models

1 code implementation CVPR 2021 Tianlong Chen, Jonathan Frankle, Shiyu Chang, Sijia Liu, Yang Zhang, Michael Carbin, Zhangyang Wang

We extend the scope of LTH and question whether matching subnetworks still exist in pre-trained computer vision models, that enjoy the same downstream transfer performance.

FASTMATCH: Accelerating the Inference of BERT-based Text Matching

no code implementations COLING 2020 Shuai Pang, Jianqiang Ma, Zeyu Yan, Yang Zhang, Jianping Shen

Recently, pre-trained language models such as BERT have shown state-of-the-art accuracies in text matching.

Text Matching

SQL Generation via Machine Reading Comprehension

1 code implementation COLING 2020 Zeyu Yan, Jianqiang Ma, Yang Zhang, Jianping Shen

Text-to-SQL systems offers natural language interfaces to databases, which can automatically generates SQL queries given natural language questions.

Machine Reading Comprehension Question Answering +3

Speech Denoising with Auditory Models

1 code implementation21 Nov 2020 Mark R. Saddler, Andrew Francl, Jenelle Feather, Kaizhi Qian, Yang Zhang, Josh H. McDermott

Contemporary speech enhancement predominantly relies on audio transforms that are trained to reconstruct a clean speech waveform.

Denoising Speech Denoising +1

Orbital ordering in the layered perovskite material CsVF$_4$

no code implementations21 Nov 2020 Ling-Fang Lin, Nitin Kaushal, Yang Zhang, Adriana Moreo, Elbio Dagotto

We show that this degeneracy is broken and a novel $d_{yz}$/$d_{xz}$ staggered orbital pattern is here predicted by both the first-principles and Hubbard model calculations.

Strongly Correlated Electrons

Improving RNN transducer with normalized jointer network

no code implementations3 Nov 2020 Mingkun Huang, Jun Zhang, Meng Cai, Yang Zhang, Jiali Yao, Yongbin You, Yi He, Zejun Ma

In this work, we analyze the cause of the huge gradient variance in RNN-T training and proposed a new \textit{normalized jointer network} to overcome it.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Dynamic latency speech recognition with asynchronous revision

no code implementations3 Nov 2020 Mingkun Huang, Meng Cai, Jun Zhang, Yang Zhang, Yongbin You, Yi He, Zejun Ma

In this work we propose an inference technique, asynchronous revision, to unify streaming and non-streaming speech recognition models.

speech-recognition Speech Recognition

Squeezing value of cross-domain labels: a decoupled scoring approach for speaker verification

no code implementations27 Oct 2020 Lantian Li, Yang Zhang, Jiawen Kang, Thomas Fang Zheng, Dong Wang

Domain mismatch often occurs in real applications and causes serious performance reduction on speaker verification systems.

Speaker Verification

Deep generative factorization for speech signal

no code implementations27 Oct 2020 Haoran Sun, Lantian Li, Yunqi Cai, Yang Zhang, Thomas Fang Zheng, Dong Wang

Various information factors are blended in speech signals, which forms the primary difficulty for most speech information processing tasks.

Double-Uncertainty Weighted Method for Semi-supervised Learning

no code implementations19 Oct 2020 Yixin Wang, Yao Zhang, Jiang Tian, Cheng Zhong, Zhongchao shi, Yang Zhang, Zhiqiang He

We train the teacher model using Bayesian deep learning to obtain double-uncertainty, i. e. segmentation uncertainty and feature uncertainty.

BioMegatron: Larger Biomedical Domain Language Model

1 code implementation EMNLP 2020 Hoo-chang Shin, Yang Zhang, Evelina Bakhturina, Raul Puri, Mostofa Patwary, Mohammad Shoeybi, Raghav Mani

There has been an influx of biomedical domain-specific language models, showing language models pre-trained on biomedical text perform better on biomedical domain benchmarks than those trained on general domain text corpora such as Wikipedia and Books.

Language Modelling named-entity-recognition +4