Search Results for author: Xin Dong

Found 38 papers, 8 papers with code

Finding needles in a haystack: A Black-Box Approach to Invisible Watermark Detection

no code implementations23 Mar 2024 Minzhou Pan, Zhengting Wang, Xin Dong, Vikash Sehwag, Lingjuan Lyu, Xue Lin

In this paper, we propose WaterMark Detection (WMD), the first invisible watermark detection method under a black-box and annotation-free setting.

Segment Every Out-of-Distribution Object

no code implementations27 Nov 2023 Wenjie Zhao, Jia Li, Xin Dong, Yu Xiang, Yunhui Guo

Semantic segmentation models, while effective for in-distribution categories, face challenges in real-world deployment due to encountering out-of-distribution (OoD) objects.

Object Segmentation +1

The Cost of Down-Scaling Language Models: Fact Recall Deteriorates before In-Context Learning

no code implementations7 Oct 2023 Tian Jin, Nolan Clement, Xin Dong, Vaishnavh Nagarajan, Michael Carbin, Jonathan Ragan-Kelley, Gintare Karolina Dziugaite

We study two natural scaling techniques -- weight pruning and simply training a smaller or larger model, which we refer to as dense scaling -- and their effects on two core capabilities of LLMs: (a) recalling facts presented during pre-training and (b) processing information presented in-context during inference.

In-Context Learning

Face Encryption via Frequency-Restricted Identity-Agnostic Attacks

no code implementations11 Aug 2023 Xin Dong, Rui Wang, Siyuan Liang, Aishan Liu, Lihua Jing

As for the weak black-box scenario feasibility, we obverse that representations of the average feature in multiple face recognition models are similar, thus we propose to utilize the average feature via the crawled dataset from the Internet as the target to guide the generation, which is also agnostic to identities of unknown face recognition systems; in nature, the low-frequency perturbations are more visually perceptible by the human vision system.

Face Recognition

GP-VTON: Towards General Purpose Virtual Try-on via Collaborative Local-Flow Global-Parsing Learning

1 code implementation CVPR 2023 Zhenyu Xie, Zaiyu Huang, Xin Dong, Fuwei Zhao, Haoye Dong, Xijin Zhang, Feida Zhu, Xiaodan Liang

Specifically, compared with the previous global warping mechanism, LFGP employs local flows to warp garments parts individually, and assembles the local warped results via the global garment parsing, resulting in reasonable warped parts and a semantic-correct intact garment even with challenging inputs. On the other hand, our DGT training strategy dynamically truncates the gradient in the overlap area and the warped garment is no more required to meet the boundary constraint, which effectively avoids the texture squeezing problem.

Virtual Try-on

GDOD: Effective Gradient Descent using Orthogonal Decomposition for Multi-Task Learning

no code implementations31 Jan 2023 Xin Dong, Ruize Wu, Chao Xiong, Hai Li, Lei Cheng, Yong He, Shiyou Qian, Jian Cao, Linjian Mo

GDOD decomposes gradients into task-shared and task-conflict components explicitly and adopts a general update rule for avoiding interference across all task gradients.

Multi-Task Learning

PASTA-GAN++: A Versatile Framework for High-Resolution Unpaired Virtual Try-on

no code implementations27 Jul 2022 Zhenyu Xie, Zaiyu Huang, Fuwei Zhao, Haoye Dong, Michael Kampffmeyer, Xin Dong, Feida Zhu, Xiaodan Liang

In this work, we take a step forwards to explore versatile virtual try-on solutions, which we argue should possess three main properties, namely, they should support unsupervised training, arbitrary garment categories, and controllable garment editing.

Disentanglement Image Generation +1

SphereFed: Hyperspherical Federated Learning

no code implementations19 Jul 2022 Xin Dong, Sai Qian Zhang, Ang Li, H. T. Kung

Federated Learning aims at training a global model from multiple decentralized devices (i. e. clients) without exchanging their private local data.

Federated Learning

DRESS: Dynamic REal-time Sparse Subnets

no code implementations1 Jul 2022 Zhongnan Qu, Syed Shakib Sarwar, Xin Dong, Yuecheng Li, Ekin Sumbul, Barbara De Salvo

The limited and dynamically varied resources on edge devices motivate us to deploy an optimized deep neural network that can adapt its sub-networks to fit in different resource constraints.

Converting Artificial Neural Networks to Spiking Neural Networks via Parameter Calibration

1 code implementation6 May 2022 Yuhang Li, Shikuang Deng, Xin Dong, Shi Gu

We demonstrate that our method can handle the SNN conversion with batch normalization layers and effectively preserve the high accuracy even in 32 time steps.

SplitNets: Designing Neural Architectures for Efficient Distributed Computing on Head-Mounted Systems

no code implementations CVPR 2022 Xin Dong, Barbara De Salvo, Meng Li, Chiao Liu, Zhongnan Qu, H. T. Kung, Ziyun Li

We design deep neural networks (DNNs) and corresponding networks' splittings to distribute DNNs' workload to camera sensors and a centralized aggregator on head mounted devices to meet system performance targets in inference accuracy and latency under the given hardware resource constraints.

3D Classification Distributed Computing +1

Dressing in the Wild by Watching Dance Videos

no code implementations CVPR 2022 Xin Dong, Fuwei Zhao, Zhenyu Xie, Xijin Zhang, Daniel K. Du, Min Zheng, Xiang Long, Xiaodan Liang, Jianchao Yang

While significant progress has been made in garment transfer, one of the most applicable directions of human-centric image generation, existing works overlook the in-the-wild imagery, presenting severe garment-person misalignment as well as noticeable degradation in fine texture details.

Image Generation Virtual Try-on

TCMPR: TCM Prescription recommendation based on subnetwork term mapping and deep learning

1 code implementation 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) 2021 Xin Dong, Yi Zheng, Zixin Shu, Kai Chang, Dengying Yan, Jianan Xia, Qiang Zhu, Kunyu Zhong, Xinyan Wang, Kuo Yang, Xuezhong Zhou

In addition, the comprehensive experiments of TCMPR with different hyper parameters (i. e., feature embedding, feature dimension and feature fusion) that demonstrates that our method has high performance on TCM prescription recommendation and potentially promote clinical diagnosis and treatment of TCM precision medicine.

Fast query-by-example speech search using separable model

no code implementations18 Sep 2021 Yuguang Yang, Yu Pan, Xin Dong, Minqiang Xu

Second, we design a novel model inference scheme based on RepVGG which can efficiently improve the QbE search quality.

Word Embeddings

Data Augmentation with Adversarial Training for Cross-Lingual NLI

no code implementations ACL 2021 Xin Dong, Yaxin Zhu, Zuohui Fu, Dongkuan Xu, Gerard de Melo

Due to recent pretrained multilingual representation models, it has become feasible to exploit labeled data from one language to train a cross-lingual model that can then be applied to multiple new languages.

Cross-Lingual Natural Language Inference Data Augmentation

Privacy Vulnerability of Split Computing to Data-Free Model Inversion Attacks

no code implementations13 Jul 2021 Xin Dong, Hongxu Yin, Jose M. Alvarez, Jan Kautz, Pavlo Molchanov, H. T. Kung

Prior works usually assume that SC offers privacy benefits as only intermediate features, instead of private data, are shared from devices to the cloud.

A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibration

1 code implementation13 Jun 2021 Yuhang Li, Shikuang Deng, Xin Dong, Ruihao Gong, Shi Gu

Moreover, our calibration algorithm can produce SNN with state-of-the-art architecture on the large-scale ImageNet dataset, including MobileNet and RegNet.

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

Domain-Specific Sentiment Lexicons Induced from Labeled Documents

no code implementations COLING 2020 Sm Mazharul Islam, Xin Dong, Gerard de Melo

Sentiment analysis is an area of substantial relevance both in industry and in academia, including for instance in social studies.

Sentiment Analysis

exBERT: Extending Pre-trained Models with Domain-specific Vocabulary Under Constrained Training Resources

no code implementations Findings of the Association for Computational Linguistics 2020 Wen Tai, H. T. Kung, Xin Dong, Marcus Comiter, Chang-Fu Kuo

We introduce exBERT, a training method to extend BERT pre-trained models from a general domain to a new pre-trained model for a specific domain with a new additive vocabulary under constrained training resources (i. e., constrained computation and data).

Leveraging Adversarial Training in Self-Learning for Cross-Lingual Text Classification

no code implementations29 Jul 2020 Xin Dong, Yaxin Zhu, Yupeng Zhang, Zuohui Fu, Dongkuan Xu, Sen yang, Gerard de Melo

The resulting model then serves as a teacher to induce labels for unlabeled target language samples that can be used during further adversarial training, allowing us to gradually adapt our model to the target language.

General Classification intent-classification +4

Efficient Bitwidth Search for Practical Mixed Precision Neural Network

no code implementations17 Mar 2020 Yuhang Li, Wei Wang, Haoli Bai, Ruihao Gong, Xin Dong, Fengwei Yu

Network quantization has rapidly become one of the most widely used methods to compress and accelerate deep neural networks.

Quantization

ABSent: Cross-Lingual Sentence Representation Mapping with Bidirectional GANs

no code implementations29 Jan 2020 Zuohui Fu, Yikun Xian, Shijie Geng, Yingqiang Ge, Yuting Wang, Xin Dong, Guang Wang, Gerard de Melo

A number of cross-lingual transfer learning approaches based on neural networks have been proposed for the case when large amounts of parallel text are at our disposal.

Cross-Lingual Transfer Sentence +3

Asymmetrical Hierarchical Networks with Attentive Interactions for Interpretable Review-Based Recommendation

no code implementations18 Dec 2019 Xin Dong, Jingchao Ni, Wei Cheng, Zhengzhang Chen, Bo Zong, Dongjin Song, Yanchi Liu, Haifeng Chen, Gerard de Melo

In practice, however, these two sets of reviews are notably different: users' reviews reflect a variety of items that they have bought and are hence very heterogeneous in their topics, while an item's reviews pertain only to that single item and are thus topically homogeneous.

Recommendation Systems

RTN: Reparameterized Ternary Network

no code implementations4 Dec 2019 Yuhang Li, Xin Dong, Sai Qian Zhang, Haoli Bai, Yuanpeng Chen, Wei Wang

We first bring up three omitted issues in extremely low-bit networks: the squashing range of quantized values; the gradient vanishing during backpropagation and the unexploited hardware acceleration of ternary networks.

Quantization

A Robust Self-Learning Framework for Cross-Lingual Text Classification

no code implementations IJCNLP 2019 Xin Dong, Gerard de Melo

Based on massive amounts of data, recent pretrained contextual representation models have made significant strides in advancing a number of different English NLP tasks.

General Classification Self-Learning +4

Additive Powers-of-Two Quantization: An Efficient Non-uniform Discretization for Neural Networks

1 code implementation ICLR 2020 Yuhang Li, Xin Dong, Wei Wang

We propose Additive Powers-of-Two~(APoT) quantization, an efficient non-uniform quantization scheme for the bell-shaped and long-tailed distribution of weights and activations in neural networks.

Computational Efficiency Quantization

Full-stack Optimization for Accelerating CNNs with FPGA Validation

no code implementations1 May 2019 Bradley McDanel, Sai Qian Zhang, H. T. Kung, Xin Dong

A highlight of our full-stack approach which attributes to the achieved high energy efficiency is an efficient Selector-Accumulator (SAC) architecture for implementing the multiplier-accumulator (MAC) operation present in any digital CNN hardware.

A Main/Subsidiary Network Framework for Simplifying Binary Neural Network

no code implementations11 Dec 2018 Yinghao Xu, Xin Dong, Yudian Li, Hao Su

To reduce memory footprint and run-time latency, techniques such as neural network pruning and binarization have been explored separately.

Binarization Image Classification +1

What and Where: A Context-based Recommendation System for Object Insertion

no code implementations24 Nov 2018 Song-Hai Zhang, Zhengping Zhou, Bin Liu, Xin Dong, Dun Liang, Peter Hall, Shi-Min Hu

In this work, we propose a novel topic consisting of two dual tasks: 1) given a scene, recommend objects to insert, 2) given an object category, retrieve suitable background scenes.

Object

A Helping Hand: Transfer Learning for Deep Sentiment Analysis

no code implementations ACL 2018 Xin Dong, Gerard de Melo

Deep convolutional neural networks excel at sentiment polarity classification, but tend to require substantial amounts of training data, which moreover differs quite significantly between domains.

General Classification Sentiment Analysis +2

Binary Ensemble Neural Network: More Bits per Network or More Networks per Bit?

1 code implementation CVPR 2019 Shilin Zhu, Xin Dong, Hao Su

Binary neural networks (BNN) have been studied extensively since they run dramatically faster at lower memory and power consumption than floating-point networks, thanks to the efficiency of bit operations.

Pose2Seg: Detection Free Human Instance Segmentation

6 code implementations CVPR 2019 Song-Hai Zhang, Rui-Long Li, Xin Dong, Paul L. Rosin, Zixi Cai, Han Xi, Dingcheng Yang, Hao-Zhi Huang, Shi-Min Hu

We demonstrate that our pose-based framework can achieve better accuracy than the state-of-art detection-based approach on the human instance segmentation problem, and can moreover better handle occlusion.

2D Human Pose Estimation Human Instance Segmentation +5

Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon

2 code implementations NeurIPS 2017 Xin Dong, Shangyu Chen, Sinno Jialin Pan

How to develop slim and accurate deep neural networks has become crucial for real- world applications, especially for those employed in embedded systems.

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