Search Results for author: Yifan Wang

Found 60 papers, 20 papers with code

CLIFFNet for Monocular Depth Estimation with Hierarchical Embedding Loss

no code implementations ECCV 2020 Lijun Wang, Jianming Zhang, Yifan Wang, Huchuan Lu, Xiang Ruan

This paper proposes a hierarchical loss for monocular depth estimation, which measures the differences between the prediction and ground truth in hierarchical embedding spaces of depth maps.

Monocular Depth Estimation

OPERA: Operation-Pivoted Discrete Reasoning over Text

1 code implementation NAACL 2022 Yongwei Zhou, Junwei Bao, Chaoqun Duan, Haipeng Sun, Jiahui Liang, Yifan Wang, Jing Zhao, Youzheng Wu, Xiaodong He, Tiejun Zhao

To inherit the advantages of these two types of methods, we propose OPERA, an operation-pivoted discrete reasoning framework, where lightweight symbolic operations (compared with logical forms) as neural modules are utilized to facilitate the reasoning ability and interpretability.

Machine Reading Comprehension Semantic Parsing

Learned Accelerator Framework for Angular-Distance-Based High-Dimensional DBSCAN

1 code implementation6 Feb 2023 Yifan Wang, Daisy Zhe Wang

In this paper, we propose LAF, a generic learned accelerator framework to speed up the original DBSCAN and the sampling-based variants of DBSCAN on high-dimensional data with angular distance metric.

Unsupervised Mandarin-Cantonese Machine Translation

1 code implementation10 Jan 2023 Megan Dare, Valentina Fajardo Diaz, Averie Ho Zoen So, Yifan Wang, Shibingfeng Zhang

Advancements in unsupervised machine translation have enabled the development of machine translation systems that can translate between languages for which there is not an abundance of parallel data available.

Translation Unsupervised Machine Translation

Automatic Generation of German Drama Texts Using Fine Tuned GPT-2 Models

no code implementations8 Jan 2023 Mariam Bangura, Kristina Barabashova, Anna Karnysheva, Sarah Semczuk, Yifan Wang

The input for the neural model comprises two datasets: the German Drama Corpus (GerDraCor) and German Text Archive (Deutsches Textarchiv or DTA).

Controlling Styles in Neural Machine Translation with Activation Prompt

1 code implementation17 Dec 2022 Yifan Wang, Zewei Sun, Shanbo Cheng, Weiguo Zheng, Mingxuan Wang

First, we re-visit this task and propose a multiway stylized machine translation (MSMT) benchmark, which includes multiple categories of styles in four language directions to push the boundary of this task.

Machine Translation NMT +1

Bandit Algorithms for Prophet Inequality and Pandora's Box

no code implementations16 Nov 2022 Khashayar Gatmiry, Thomas Kesselheim, Sahil Singla, Yifan Wang

The goal is to minimize the regret, which is the difference over $T$ rounds in the total value of the optimal algorithm that knows the distributions vs. the total value of our algorithm that learns the distributions from the partial feedback.

Multi-Armed Bandits Stochastic Optimization

P$^3$LM: Probabilistically Permuted Prophet Language Modeling for Generative Pre-Training

no code implementations22 Oct 2022 Junwei Bao, Yifan Wang, Jiangyong Ying, Yeyun Gong, Jing Zhao, Youzheng Wu, Xiaodong He

Conventional autoregressive left-to-right (L2R) sequence generation faces two issues during decoding: limited to unidirectional target sequence modeling, and constrained on strong local dependencies.

Conversational Question Answering Language Modelling +3

Kernel-based Substructure Exploration for Next POI Recommendation

1 code implementation8 Oct 2022 Wei Ju, Yifang Qin, Ziyue Qiao, Xiao Luo, Yifan Wang, Yanjie Fu, Ming Zhang

To tackle the above issues, we propose a Kernel-Based Graph Neural Network (KBGNN) for next POI recommendation, which combines the characteristics of both geographical and sequential influences in a collaborative way.

Recommendation Systems

Lightweight Image Codec via Multi-Grid Multi-Block-Size Vector Quantization (MGBVQ)

no code implementations25 Sep 2022 Yifan Wang, Zhanxuan Mei, Ioannis Katsavounidis, C. -C. Jay Kuo

The fundamental idea of image coding is to remove correlations among pixels before quantization and entropy coding, e. g., the discrete cosine transform (DCT) and intra predictions, adopted by modern image coding standards.


Learning the Propagation of Worms in Wireless Sensor Networks

no code implementations20 Sep 2022 Yifan Wang, Siqi Wang, Guangmo Tong

Wireless sensor networks (WSNs) are composed of spatially distributed sensors and are considered vulnerable to attacks by worms and their variants.

Deep-Steiner: Learning to Solve the Euclidean Steiner Tree Problem

1 code implementation20 Sep 2022 Siqi Wang, Yifan Wang, Guangmo Tong

The Euclidean Steiner tree problem seeks the min-cost network to connect a collection of target locations, and it underlies many applications of wireless networks.

Graph Representation Learning Steiner Tree Problem

Provably Uncertainty-Guided Universal Domain Adaptation

no code implementations19 Sep 2022 Yifan Wang, Lin Zhang, Ran Song, Wei zhang

Then, based on the estimation, we propose a novel neighbors searching method in the linear subspace with a $\delta$-filter to estimate the uncertainty score of a target sample and discover unknown samples.

Universal Domain Adaptation Unsupervised Domain Adaptation

A Knowledge Distillation-Based Backdoor Attack in Federated Learning

no code implementations12 Aug 2022 Yifan Wang, Wei Fan, Keke Yang, Naji Alhusaini, Jing Li

With knowledge distillation, we can reduce the abnormal characteristics in model result from the label flipping, thus the model can bypass the defenses.

Backdoor Attack Federated Learning +1

Exploiting Inter-Sample Affinity for Knowability-Aware Universal Domain Adaptation

no code implementations19 Jul 2022 Yifan Wang, Lin Zhang, Ran Song, Hongliang Li, Paul L. Rosin, Wei zhang

Specifically, we introduce a knowability-based labeling scheme which can be divided into two steps: 1) Knowability-guided detection of known and unknown samples based on the intrinsic structure of the neighborhoods of samples, where we leverage the first singular vectors of the affinity matrices to obtain the knowability of every target sample.

Universal Domain Adaptation

Vertical GaN Diode BV Maximization through Rapid TCAD Simulation and ML-enabled Surrogate Model

no code implementations18 Jul 2022 Albert Lu, Jordan Marshall, Yifan Wang, Ming Xiao, Yuhao Zhang, Hiu Yung Wong

In this paper, two methodologies are used to speed up the maximization of the breakdown volt-age (BV) of a vertical GaN diode that has a theoretical maximum BV of ~2100V.

A Survey on the Fairness of Recommender Systems

no code implementations8 Jun 2022 Yifan Wang, Weizhi Ma, Min Zhang, Yiqun Liu, Shaoping Ma

First, we summarize fairness definitions in the recommendation and provide several views to classify fairness issues.

Fairness Recommendation Systems

Learnability of Competitive Threshold Models

1 code implementation8 May 2022 Yifan Wang, Guangmo Tong

Modeling the spread of social contagions is central to various applications in social computing.

Generalization Bounds

LIDER: An Efficient High-dimensional Learned Index for Large-scale Dense Passage Retrieval

no code implementations2 May 2022 Yifan Wang, Haodi Ma, Daisy Zhe Wang

As the basic unit of LIDER to index and search data, a core model includes an adapted recursive model index (RMI) and a dimension reduction component which consists of an extended SortingKeys-LSH (SK-LSH) and a key re-scaling module.

Dimensionality Reduction Passage Retrieval +1

OPERA:Operation-Pivoted Discrete Reasoning over Text

no code implementations29 Apr 2022 Yongwei Zhou, Junwei Bao, Chaoqun Duan, Haipeng Sun, Jiahui Liang, Yifan Wang, Jing Zhao, Youzheng Wu, Xiaodong He, Tiejun Zhao

To inherit the advantages of these two types of methods, we propose OPERA, an operation-pivoted discrete reasoning framework, where lightweight symbolic operations (compared with logical forms) as neural modules are utilized to facilitate the reasoning ability and interpretability.

Machine Reading Comprehension Semantic Parsing

A Survey on Efficient Processing of Similarity Queries over Neural Embeddings

no code implementations17 Apr 2022 Yifan Wang

Embedding techniques work by representing the raw data objects as vectors (so called "embeddings" or "neural embeddings" since they are mostly generated by neural network models) that expose the hidden semantics of the raw data, based on which embeddings do show outstanding effectiveness on capturing data similarities, making it one of the most widely used and studied techniques in the state-of-the-art similarity query processing research.

Entity Resolution Information Retrieval +1

SunStage: Portrait Reconstruction and Relighting using the Sun as a Light Stage

no code implementations7 Apr 2022 Yifan Wang, Aleksander Holynski, Xiuming Zhang, Xuaner Zhang

Our method only requires the user to capture a selfie video outdoors, rotating in place, and uses the varying angles between the sun and the face as guidance in joint reconstruction of facial geometry, reflectance, camera pose, and lighting parameters.

Novel View Synthesis

Fine- and Coarse-Granularity Hybrid Self-Attention for Efficient BERT

1 code implementation ACL 2022 Jing Zhao, Yifan Wang, Junwei Bao, Youzheng Wu, Xiaodong He

To confront this, we propose FCA, a fine- and coarse-granularity hybrid self-attention that reduces the computation cost through progressively shortening the computational sequence length in self-attention.


Back to Reality: Weakly-supervised 3D Object Detection with Shape-guided Label Enhancement

2 code implementations CVPR 2022 Xiuwei Xu, Yifan Wang, Yu Zheng, Yongming Rao, Jie zhou, Jiwen Lu

In this paper, we propose a weakly-supervised approach for 3D object detection, which makes it possible to train a strong 3D detector with position-level annotations (i. e. annotations of object centers).

3D Object Detection Domain Adaptation +1

Multiscale Convolutional Transformer with Center Mask Pretraining for Hyperspectral Image Classification

no code implementations9 Mar 2022 Sen Jia, Yifan Wang

However, CNN-based methods are difficult to capture long-range dependencies, and also require a large amount of labeled data for model training. Besides, most of the self-supervised training methods in the field of HSI classification are based on the reconstruction of input samples, and it is difficult to achieve effective use of unlabeled samples.

Classification Hyperspectral Image Classification

MuSCLe: A Multi-Strategy Contrastive Learning Framework for Weakly Supervised Semantic Segmentation

no code implementations18 Jan 2022 Kunhao Yuan, Gerald Schaefer, Yu-Kun Lai, Yifan Wang, Xiyao Liu, Lin Guan, Hui Fang

Weakly supervised semantic segmentation (WSSS) has gained significant popularity since it relies only on weak labels such as image level annotations rather than pixel level annotations required by supervised semantic segmentation (SSS) methods.

Contrastive Learning Weakly supervised Semantic Segmentation +1

Multi-Source Uncertainty Mining for Deep Unsupervised Saliency Detection

no code implementations CVPR 2022 Yifan Wang, Wenbo Zhang, Lijun Wang, Ting Liu, Huchuan Lu

We design an Uncertainty Mining Network (UMNet) which consists of multiple Merge-and-Split (MS) modules to recursively analyze the commonality and difference among multiple noisy labels and infer pixel-wise uncertainty map for each label.

object-detection Object Detection +3

CUSTOM: Aspect-Oriented Product Summarization for E-Commerce

1 code implementation18 Aug 2021 Jiahui Liang, Junwei Bao, Yifan Wang, Youzheng Wu, Xiaodong He, BoWen Zhou

To address the problem, we propose CUSTOM, aspect-oriented product summarization for e-commerce, which generates diverse and controllable summaries towards different product aspects.

DisenHAN: Disentangled Heterogeneous Graph Attention Network for Recommendation

1 code implementation21 Jun 2021 Yifan Wang, Suyao Tang, Yuntong Lei, Weiping Song, Sheng Wang, Ming Zhang

In this paper, we propose a novel disentangled heterogeneous graph attention network DisenHAN for top-$N$ recommendation, which learns disentangled user/item representations from different aspects in a heterogeneous information network.

Collaborative Filtering Graph Attention +1

SGG: Learning to Select, Guide, and Generate for Keyphrase Generation

1 code implementation NAACL 2021 Jing Zhao, Junwei Bao, Yifan Wang, Youzheng Wu, Xiaodong He, BoWen Zhou

Keyphrases, that concisely summarize the high-level topics discussed in a document, can be categorized into present keyphrase which explicitly appears in the source text, and absent keyphrase which does not match any contiguous subsequence but is highly semantically related to the source.

Keyphrase Generation Text Generation

DynOcc: Learning Single-View Depth from Dynamic Occlusion Cues

no code implementations30 Mar 2021 Yifan Wang, Linjie Luo, Xiaohui Shen, Xing Mei

Recently, significant progress has been made in single-view depth estimation thanks to increasingly large and diverse depth datasets.

3D Reconstruction Autonomous Driving +2

Repopulating Street Scenes

no code implementations CVPR 2021 Yifan Wang, Andrew Liu, Richard Tucker, Jiajun Wu, Brian L. Curless, Steven M. Seitz, Noah Snavely

We present a framework for automatically reconfiguring images of street scenes by populating, depopulating, or repopulating them with objects such as pedestrians or vehicles.

Autonomous Driving

Defect $a$-Theorem and $a$-Maximization

no code implementations29 Jan 2021 Yifan Wang

We derive the anomaly multiplet relations that express the defect $a$- and $c$-anomalies in terms of the defect (mixed) 't Hooft anomalies for this $U(1)_R$ symmetry.

High Energy Physics - Theory

Anomalous Symmetries End at the Boundary

no code implementations31 Dec 2020 Ryan Thorngren, Yifan Wang

We then recast the problem in terms of symmetry defects and find the same conclusions for anomalies of discrete and orientation-reversing global symmetries, up to the conjecture that global gravitational anomalies, which may not be associated with any diffeomorphism symmetry, also forbid the existence of boundary conditions.

High Energy Physics - Theory Strongly Correlated Electrons

Surface Defect, Anomalies and $b$-Extremization

no code implementations11 Dec 2020 Yifan Wang

The $b$-theorem states that $b$ must monotonically decrease under defect RG flows and was proven by coupling to a spurious defect dilaton.

High Energy Physics - Theory

Low-Resolution Face Recognition In Resource-Constrained Environments

no code implementations23 Nov 2020 Mozhdeh Rouhsedaghat, Yifan Wang, Shuowen Hu, Suya You, C. -C. Jay Kuo

A non-parametric low-resolution face recognition model for resource-constrained environments with limited networking and computing is proposed in this work.

Active Learning Face Recognition

VC-Net: Deep Volume-Composition Networks for Segmentation and Visualization of Highly Sparse and Noisy Image Data

no code implementations14 Sep 2020 Yifan Wang, Guoli Yan, Haikuan Zhu, Sagar Buch, Ying Wang, Ewart Mark Haacke, Jing Hua, Zichun Zhong

A multi-stream convolutional neural network is proposed to learn the 3D volume and 2D MIP features respectively and then explore their inter-dependencies in a joint volume-composition embedding space by unprojecting the MIP features into 3D volume embedding space.

FaceHop: A Light-Weight Low-Resolution Face Gender Classification Method

no code implementations18 Jul 2020 Mozhdeh Rouhsedaghat, Yifan Wang, Xiou Ge, Shuowen Hu, Suya You, C. -C. Jay Kuo

For gray-scale face images of resolution $32 \times 32$ in the LFW and the CMU Multi-PIE datasets, FaceHop achieves correct gender classification rates of 94. 63% and 95. 12% with model sizes of 16. 9K and 17. 6K parameters, respectively.

Classification General Classification

People as Scene Probes

no code implementations ECCV 2020 Yifan Wang, Brian Curless, Steve Seitz

By analyzing the motion of people and other objects in a scene, we demonstrate how to infer depth, occlusion, lighting, and shadow information from video taken from a single camera viewpoint.

Depth Estimation

Attention: to Better Stand on the Shoulders of Giants

no code implementations27 May 2020 Sha Yuan, Zhou Shao, Yu Zhang, Xingxing Wei, Tong Xiao, Yifan Wang, Jie Tang

In the progress of science, the previously discovered knowledge principally inspires new scientific ideas, and citation is a reasonably good reflection of this cumulative nature of scientific research.

PointHop++: A Lightweight Learning Model on Point Sets for 3D Classification

2 code implementations9 Feb 2020 Min Zhang, Yifan Wang, Pranav Kadam, Shan Liu, C. -C. Jay Kuo

The PointHop method was recently proposed by Zhang et al. for 3D point cloud classification with unsupervised feature extraction.

3D Classification 3D Point Cloud Classification +2

OpenEI: An Open Framework for Edge Intelligence

no code implementations5 Jun 2019 Xingzhou Zhang, Yifan Wang, Sidi Lu, Liangkai Liu, Lanyu Xu, Weisong Shi

At the same time, we have witnessed the proliferation of AI algorithms and models which accelerate the successful deployment of intelligence mainly in cloud services.


pCAMP: Performance Comparison of Machine Learning Packages on the Edges

no code implementations5 Jun 2019 Xingzhou Zhang, Yifan Wang, Weisong Shi

However, little research has been done to evaluate these packages on the edges, making it difficult for end users to select an appropriate pair of software and hardware.

BIG-bench Machine Learning

Session-based Social Recommendation via Dynamic Graph Attention Networks

2 code implementations25 Feb 2019 Weiping Song, Zhiping Xiao, Yifan Wang, Laurent Charlin, Ming Zhang, Jian Tang

However, recommendation in online communities is a challenging problem: 1) users' interests are dynamic, and 2) users are influenced by their friends.

 Ranked #1 on Recommendation Systems on Douban (NDCG metric)

Graph Attention Recommendation Systems

Dual Principal Component Pursuit: Probability Analysis and Efficient Algorithms

no code implementations24 Dec 2018 Zhihui Zhu, Yifan Wang, Daniel P. Robinson, Daniel Q. Naiman, Rene Vidal, Manolis C. Tsakiris

However, its geometric analysis is based on quantities that are difficult to interpret and are not amenable to statistical analysis.

Dual Principal Component Pursuit: Improved Analysis and Efficient Algorithms

no code implementations NeurIPS 2018 Zhihui Zhu, Yifan Wang, Daniel Robinson, Daniel Naiman, Rene Vidal, Manolis Tsakiris

However, its geometric analysis is based on quantities that are difficult to interpret and are not amenable to statistical analysis.

Modeling and Predicting Citation Count via Recurrent Neural Network with Long Short-Term Memory

no code implementations6 Nov 2018 Sha Yuan, Jie Tang, Yu Zhang, Yifan Wang, Tong Xiao

The rapid evolution of scientific research has been creating a huge volume of publications every year.

Digital Libraries Physics and Society

CAVBench: A Benchmark Suite for Connected and Autonomous Vehicles

no code implementations15 Oct 2018 Yifan Wang, Shaoshan Liu, Xiaopei Wu, Weisong Shi

Meanwhile, several pioneer efforts have focused on the edge computing system and architecture design for the CAVs scenario and provided various heterogeneous platform prototypes for CAVs.

Distributed, Parallel, and Cluster Computing Performance

A Fully Progressive Approach to Single-Image Super-Resolution

6 code implementations9 Apr 2018 Yifan Wang, Federico Perazzi, Brian McWilliams, Alexander Sorkine-Hornung, Olga Sorkine-Hornung, Christopher Schroers

Recent deep learning approaches to single image super-resolution have achieved impressive results in terms of traditional error measures and perceptual quality.

Image Super-Resolution SSIM

Identifying Outlier Arms in Multi-Armed Bandit

no code implementations NeurIPS 2017 Honglei Zhuang, Chi Wang, Yifan Wang

Outlier detection is a powerful method to narrow down the attention to a few objects after the data for them are collected.

Outlier Detection

MarrNet: 3D Shape Reconstruction via 2.5D Sketches

no code implementations NeurIPS 2017 Jiajun Wu, Yifan Wang, Tianfan Xue, Xingyuan Sun, William T. Freeman, Joshua B. Tenenbaum

First, compared to full 3D shape, 2. 5D sketches are much easier to be recovered from a 2D image; models that recover 2. 5D sketches are also more likely to transfer from synthetic to real data.

3D Object Reconstruction From A Single Image 3D Reconstruction +2

(2,2) Superconformal Bootstrap in Two Dimensions

no code implementations17 Oct 2016 Ying-Hsuan Lin, Shu-Heng Shao, Yifan Wang, Xi Yin

We find a simple relation between two-dimensional BPS N=2 superconformal blocks and bosonic Virasoro conformal blocks, which allows us to analyze the crossing equations for BPS 4-point functions in unitary (2, 2) superconformal theories numerically with semidefinite programming.

High Energy Physics - Theory

End-to-End Image Super-Resolution via Deep and Shallow Convolutional Networks

no code implementations26 Jul 2016 Yifan Wang, Lijun Wang, Hongyu Wang, Peihua Li

In this paper, we seek an alternative and propose a new image SR method, which jointly learns the feature extraction, upsampling and HR reconstruction modules, yielding a completely end-to-end trainable deep CNN.

Image Super-Resolution

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