Search Results for author: Fan Yang

Found 198 papers, 74 papers with code

Beyond 3DMM Space: Towards Fine-grained 3D Face Reconstruction

1 code implementation ECCV 2020 Xiangyu Zhu, Fan Yang, Di Huang, Chang Yu, Hao Wang, Jianzhu Guo, Zhen Lei, Stan Z. Li

However, most of their training data is constructed by 3D Morphable Model, whose space spanned is only a small part of the shape space.

3D Face Reconstruction

Improving Evidence Retrieval with Claim-Evidence Entailment

no code implementations RANLP 2021 Fan Yang, Eduard Dragut, Arjun Mukherjee

Claim verification is challenging because it requires first to find textual evidence and then apply claim-evidence entailment to verify a claim.

Claim Verification Retrieval

DESED: Dialogue-based Explanation for Sentence-level Event Detection

1 code implementation COLING 2022 Yinyi Wei, Shuaipeng Liu, Jianwei Lv, Xiangyu Xi, Hailei Yan, Wei Ye, Tong Mo, Fan Yang, Guanglu Wan

Many recent sentence-level event detection efforts focus on enriching sentence semantics, e. g., via multi-task or prompt-based learning.

Dialogue Generation Event Detection

Improving Relevance Quality in Product Search using High-Precision Query-Product Semantic Similarity

no code implementations ECNLP (ACL) 2022 Alireza Bagheri Garakani, Fan Yang, Wen-Yu Hua, Yetian Chen, Michinari Momma, Jingyuan Deng, Yan Gao, Yi Sun

Ensuring relevance quality in product search is a critical task as it impacts the customer’s ability to find intended products in the short-term as well as the general perception and trust of the e-commerce system in the long term.

Re-Ranking Semantic Similarity +1

Spelling Correction using Phonetics in E-commerce Search

no code implementations ECNLP (ACL) 2022 Fan Yang, Alireza Bagheri Garakani, Yifei Teng, Yan Gao, Jia Liu, Jingyuan Deng, Yi Sun

In E-commerce search, spelling correction plays an important role to find desired products for customers in processing user-typed search queries.

Spelling Correction

Conditional generalized quantiles based on expected utility model and equivalent characterization of properties

no code implementations29 Jan 2023 Qinyu Wu, Fan Yang, Ping Zhang

As a counterpart to the (static) risk measures of generalized quantiles and motivated by Bellini et al. (2018), we propose a new kind of conditional risk measure called conditional generalized quantiles.

SparDA: Accelerating Dynamic Sparse Deep Neural Networks via Sparse-Dense Transformation

no code implementations26 Jan 2023 Ningxin Zheng, Huiqiang Jiang, Quanlu Zhang, Zhenhua Han, Yuqing Yang, Lingxiao Ma, Fan Yang, Lili Qiu, Mao Yang, Lidong Zhou

The property enables Spider (1) to extract dynamic sparsity patterns of tensors that are only known at runtime with little overhead; and (2) to transform the dynamic sparse computation into an equivalent dense computation which has been extremely optimized on commodity accelerators.

Data-centric AI: Perspectives and Challenges

no code implementations12 Jan 2023 Daochen Zha, Zaid Pervaiz Bhat, Kwei-Herng Lai, Fan Yang, Xia Hu

The role of data in building AI systems has recently been significantly magnified by the emerging concept of data-centric AI (DCAI), which advocates a fundamental shift from model advancements to ensuring data quality and reliability.

Towards Blind Watermarking: Combining Invertible and Non-invertible Mechanisms

1 code implementation24 Dec 2022 Rui Ma, Mengxi Guo, Yi Hou, Fan Yang, Yuan Li, Huizhu Jia, Xiaodong Xie

The CIN is composed of the invertible part to achieve high imperceptibility and the non-invertible part to strengthen the robustness against strong noise attacks.

Exploring Stochastic Autoregressive Image Modeling for Visual Representation

1 code implementation3 Dec 2022 Yu Qi, Fan Yang, Yousong Zhu, Yufei Liu, Liwei Wu, Rui Zhao, Wei Li

By introducing stochastic prediction and the parallel encoder-decoder, SAIM significantly improve the performance of autoregressive image modeling.

Self-Supervised Learning

Instance-level Heterogeneous Domain Adaptation for Limited-labeled Sketch-to-Photo Retrieval

1 code implementation IEEE Transactions on Multimedia 2020 Fan Yang, Yang Wu, Zheng Wang, Xiang Li, Sakriani Sakti, Satoshi Nakamura

Therefore, previous works pre-train their models on rich-labeled photo retrieval data (i. e., source domain) and then fine-tune them on the limited-labeled sketch-to-photo retrieval data (i. e., target domain).

Domain Adaptation Image Retrieval +1

MUSIED: A Benchmark for Event Detection from Multi-Source Heterogeneous Informal Texts

1 code implementation25 Nov 2022 Xiangyu Xi, Jianwei Lv, Shuaipeng Liu, Wei Ye, Fan Yang, Guanglu Wan

As a pioneering exploration that expands event detection to the scenarios involving informal and heterogeneous texts, we propose a new large-scale Chinese event detection dataset based on user reviews, text conversations, and phone conversations in a leading e-commerce platform for food service.

Event Detection

Hard to Track Objects with Irregular Motions and Similar Appearances? Make It Easier by Buffering the Matching Space

no code implementations24 Nov 2022 Fan Yang, Shigeyuki Odashima, Shoichi Masui, Shan Jiang

To address this issue, our C-BIoU tracker adds buffers to expand the matching space of detections and tracks, which mitigates the effect of irregular motions in two aspects: one is to directly match identical but non-overlapping detections and tracks in adjacent frames, and the other is to compensate for the motion estimation bias in the matching space.

Motion Estimation Multi-Object Tracking +1

The Second-place Solution for CVPR 2022 SoccerNet Tracking Challenge

no code implementations24 Nov 2022 Fan Yang, Shigeyuki Odashima, Shoichi Masui, Shan Jiang

This is our second-place solution for CVPR 2022 SoccerNet Tracking Challenge.

A Unified Model for Video Understanding and Knowledge Embedding with Heterogeneous Knowledge Graph Dataset

no code implementations19 Nov 2022 Jiaxin Deng, Dong Shen, Haojie Pan, Xiangyu Wu, Ximan Liu, Gaofeng Meng, Fan Yang, Size Li, Ruiji Fu, Zhongyuan Wang

Furthermore, based on this dataset, we propose an end-to-end model that jointly optimizes the video understanding objective with knowledge graph embedding, which can not only better inject factual knowledge into video understanding but also generate effective multi-modal entity embedding for KG.

Common Sense Reasoning Knowledge Graph Embedding +4

Self-distillation with Online Diffusion on Batch Manifolds Improves Deep Metric Learning

1 code implementation14 Nov 2022 Zelong Zeng, Fan Yang, Hong Liu, Shin'ichi Satoh

However, this type of method normally ignores the crucial knowledge hidden in the data (e. g., intra-class information variation), which is harmful to the generalization of the trained model.

Metric Learning

Deep-Learning-Empowered Inverse Design for Freeform Reconfigurable Metasurfaces

no code implementations11 Nov 2022 Changhao Liu, Fan Yang, Maokun Li, Shenheng Xu

Recently, artificial neural network empowered inverse design for metasurfaces has been developed that can design on-demand meta-atoms with diverse shapes and high performance, where the design process based on artificial intelligence is fast and automatic.

ISA-Net: Improved spatial attention network for PET-CT tumor segmentation

no code implementations4 Nov 2022 Zhengyong Huang, Sijuan Zou, Guoshuai Wang, Zixiang Chen, Hao Shen, HaiYan Wang, Na Zhang, Lu Zhang, Fan Yang, Haining Wangg, Dong Liang, Tianye Niu, Xiaohua Zhuc, Zhanli Hua

In this paper, we propose a deep learning segmentation method based on multimodal positron emission tomography-computed tomography (PET-CT), which combines the high sensitivity of PET and the precise anatomical information of CT. We design an improved spatial attention network(ISA-Net) to increase the accuracy of PET or CT in detecting tumors, which uses multi-scale convolution operation to extract feature information and can highlight the tumor region location information and suppress the non-tumor region location information.

STS Tumor Segmentation

Ground Plane Matters: Picking Up Ground Plane Prior in Monocular 3D Object Detection

no code implementations3 Nov 2022 Fan Yang, Xinhao Xu, Hui Chen, Yuchen Guo, Jungong Han, Kai Ni, Guiguang Ding

To pick up the ground plane prior for M3OD, we propose a Ground Plane Enhanced Network (GPENet) which resolves both issues at one go.

Monocular 3D Object Detection object-detection

Revisiting Attention Weights as Explanations from an Information Theoretic Perspective

no code implementations31 Oct 2022 Bingyang Wen, K. P. Subbalakshmi, Fan Yang

Attention mechanisms have recently demonstrated impressive performance on a range of NLP tasks, and attention scores are often used as a proxy for model explainability.

Deep Attention

SIMPLE-RC: Group Network Inference with Non-Sharp Nulls and Weak Signals

no code implementations31 Oct 2022 Jianqing Fan, Yingying Fan, Jinchi Lv, Fan Yang

To address these practical challenges, in this paper we propose a SIMPLE method with random coupling (SIMPLE-RC) for testing the non-sharp null hypothesis that a group of given nodes share similar (not necessarily identical) membership profiles under weaker signals.

Forecasting Human Trajectory from Scene History

1 code implementation17 Oct 2022 Mancheng Meng, Ziyan Wu, Terrence Chen, Xiran Cai, Xiang Sean Zhou, Fan Yang, Dinggang Shen

We categorize scene history information into two types: historical group trajectory and individual-surroundings interaction.

Trajectory Prediction

SoccerNet 2022 Challenges Results

6 code implementations5 Oct 2022 Silvio Giancola, Anthony Cioppa, Adrien Deliège, Floriane Magera, Vladimir Somers, Le Kang, Xin Zhou, Olivier Barnich, Christophe De Vleeschouwer, Alexandre Alahi, Bernard Ghanem, Marc Van Droogenbroeck, Abdulrahman Darwish, Adrien Maglo, Albert Clapés, Andreas Luyts, Andrei Boiarov, Artur Xarles, Astrid Orcesi, Avijit Shah, Baoyu Fan, Bharath Comandur, Chen Chen, Chen Zhang, Chen Zhao, Chengzhi Lin, Cheuk-Yiu Chan, Chun Chuen Hui, Dengjie Li, Fan Yang, Fan Liang, Fang Da, Feng Yan, Fufu Yu, Guanshuo Wang, H. Anthony Chan, He Zhu, Hongwei Kan, Jiaming Chu, Jianming Hu, Jianyang Gu, Jin Chen, João V. B. Soares, Jonas Theiner, Jorge De Corte, José Henrique Brito, Jun Zhang, Junjie Li, Junwei Liang, Leqi Shen, Lin Ma, Lingchi Chen, Miguel Santos Marques, Mike Azatov, Nikita Kasatkin, Ning Wang, Qiong Jia, Quoc Cuong Pham, Ralph Ewerth, Ran Song, RenGang Li, Rikke Gade, Ruben Debien, Runze Zhang, Sangrok Lee, Sergio Escalera, Shan Jiang, Shigeyuki Odashima, Shimin Chen, Shoichi Masui, Shouhong Ding, Sin-wai Chan, Siyu Chen, Tallal El-Shabrawy, Tao He, Thomas B. Moeslund, Wan-Chi Siu, Wei zhang, Wei Li, Xiangwei Wang, Xiao Tan, Xiaochuan Li, Xiaolin Wei, Xiaoqing Ye, Xing Liu, Xinying Wang, Yandong Guo, YaQian Zhao, Yi Yu, YingYing Li, Yue He, Yujie Zhong, Zhenhua Guo, Zhiheng Li

The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team.

Action Spotting Camera Calibration +3

Obj2Seq: Formatting Objects as Sequences with Class Prompt for Visual Tasks

1 code implementation28 Sep 2022 Zhiyang Chen, Yousong Zhu, Zhaowen Li, Fan Yang, Wei Li, Haixin Wang, Chaoyang Zhao, Liwei Wu, Rui Zhao, Jinqiao Wang, Ming Tang

Obj2Seq is able to flexibly determine input categories to satisfy customized requirements, and be easily extended to different visual tasks.

Multi-Label Classification Object Detection +1

Nesting Forward Automatic Differentiation for Memory-Efficient Deep Neural Network Training

no code implementations22 Sep 2022 Cong Guo, Yuxian Qiu, Jingwen Leng, Chen Zhang, Ying Cao, Quanlu Zhang, Yunxin Liu, Fan Yang, Minyi Guo

An activation function is an element-wise mathematical function and plays a crucial role in deep neural networks (DNN).

UMIX: Improving Importance Weighting for Subpopulation Shift via Uncertainty-Aware Mixup

1 code implementation19 Sep 2022 Zongbo Han, Zhipeng Liang, Fan Yang, Liu Liu, Lanqing Li, Yatao Bian, Peilin Zhao, Bingzhe Wu, Changqing Zhang, Jianhua Yao

Importance reweighting is a normal way to handle the subpopulation shift issue by imposing constant or adaptive sampling weights on each sample in the training dataset.

Generalization Bounds

ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network Quantization

1 code implementation30 Aug 2022 Cong Guo, Chen Zhang, Jingwen Leng, Zihan Liu, Fan Yang, Yunxin Liu, Minyi Guo, Yuhao Zhu

In this work, we propose a fixed-length adaptive numerical data type called ANT to achieve low-bit quantization with tiny hardware overheads.

Quantization

Surrogate-assisted Multi-objective Neural Architecture Search for Real-time Semantic Segmentation

no code implementations14 Aug 2022 Zhichao Lu, Ran Cheng, Shihua Huang, Haoming Zhang, Changxiao Qiu, Fan Yang

The main challenges of applying NAS to semantic segmentation arise from two aspects: (i) high-resolution images to be processed; (ii) additional requirement of real-time inference speed (i. e., real-time semantic segmentation) for applications such as autonomous driving.

Autonomous Driving Image Classification +2

Differentially Private Counterfactuals via Functional Mechanism

no code implementations4 Aug 2022 Fan Yang, Qizhang Feng, Kaixiong Zhou, Jiahao Chen, Xia Hu

Counterfactual, serving as one emerging type of model explanation, has attracted tons of attentions recently from both industry and academia.

Improving Generalization of Metric Learning via Listwise Self-distillation

1 code implementation17 Jun 2022 Zelong Zeng, Fan Yang, Zheng Wang, Shin'ichi Satoh

Most deep metric learning (DML) methods employ a strategy that forces all positive samples to be close in the embedding space while keeping them away from negative ones.

Metric Learning

Accelerating Shapley Explanation via Contributive Cooperator Selection

1 code implementation17 Jun 2022 Guanchu Wang, Yu-Neng Chuang, Mengnan Du, Fan Yang, Quan Zhou, Pushkar Tripathi, Xuanting Cai, Xia Hu

Even though Shapley value provides an effective explanation for a DNN model prediction, the computation relies on the enumeration of all possible input feature coalitions, which leads to the exponentially growing complexity.

Learning Interpretable Decision Rule Sets: A Submodular Optimization Approach

no code implementations NeurIPS 2021 Fan Yang, Kai He, Linxiao Yang, Hongxia Du, Jingbang Yang, Bo Yang, Liang Sun

The learning problem is framed as a subset selection task in which a subset of all possible rules needs to be selected to form an accurate and interpretable rule set.

Tutel: Adaptive Mixture-of-Experts at Scale

2 code implementations7 Jun 2022 Changho Hwang, Wei Cui, Yifan Xiong, Ziyue Yang, Ze Liu, Han Hu, Zilong Wang, Rafael Salas, Jithin Jose, Prabhat Ram, Joe Chau, Peng Cheng, Fan Yang, Mao Yang, Yongqiang Xiong

On effectiveness, the SwinV2-MoE model achieves superior accuracy in both pre-training and down-stream computer vision tasks such as COCO object detection than the counterpart dense model, indicating the readiness of Tutel for end-to-end real-world model training and inference.

Object Detection

Geo-Localization via Ground-to-Satellite Cross-View Image Retrieval

no code implementations22 May 2022 Zelong Zeng, Zheng Wang, Fan Yang, Shin'ichi Satoh

The large variation of viewpoint and irrelevant content around the target always hinder accurate image retrieval and its subsequent tasks.

Image Retrieval Representation Learning +1

Demo: low-power communications based on RIS and AI for 6G

no code implementations21 May 2022 Mingyao Cui, Zidong Wu, Yuhao Chen, Shenheng Xu, Fan Yang, Linglong Dai

By jointly designing the hardware and software, this prototype can realize real-time 4K video transmission with much reduced power consumption.

NMA: Neural Multi-slot Auctions with Externalities for Online Advertising

no code implementations20 May 2022 Guogang Liao, Xuejian Li, Ze Wang, Fan Yang, Muzhi Guan, Bingqi Zhu, Yongkang Wang, Xingxing Wang, Dong Wang

We design a list-wise deep rank module to guarantee incentive compatibility in end-to-end learning.

A Low-Cost, Controllable and Interpretable Task-Oriented Chatbot: With Real-World After-Sale Services as Example

no code implementations13 May 2022 Xiangyu Xi, Chenxu Lv, Yuncheng Hua, Wei Ye, Chaobo Sun, Shuaipeng Liu, Fan Yang, Guanglu Wan

Though widely used in industry, traditional task-oriented dialogue systems suffer from three bottlenecks: (i) difficult ontology construction (e. g., intents and slots); (ii) poor controllability and interpretability; (iii) annotation-hungry.

Chatbot Task-Oriented Dialogue Systems

Limited-memory BFGS Optimisation of Phase-Only Computer-Generated Hologram for Fraunhofer Diffraction

no code implementations10 May 2022 Jinze Sha, Andrew Kadis, Fan Yang, Timothy D. Wilkinson

We implement a novel limited-memory Broyden-Fletcher-Goldfarb-Shanno (L-BFGS) optimisation algorithm with cross entropy (CE) loss function, to produce phase-only computer-generated hologram (CGH) for holographic displays, with validation on a binary-phase modulation holographic projector.

Learning Individual Interactions from Population Dynamics with Discrete-Event Simulation Model

no code implementations4 May 2022 Yan Shen, Fan Yang, Mingchen Gao, Wen Dong

Traditional machine learning approaches capture complex system dynamics either with dynamic Bayesian networks and state space models, which is hard to scale because it is non-trivial to prescribe the dynamics with a sparse graph or a system of differential equations; or a deep neural networks, where the distributed representation of the learned dynamics is hard to interpret.

A Multi-Person Video Dataset Annotation Method of Spatio-Temporally Actions

1 code implementation21 Apr 2022 Fan Yang

Spatio-temporal action detection is an important and challenging problem in video understanding.

Action Detection Video Understanding

SC^2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration

1 code implementation28 Mar 2022 Zhi Chen, Kun Sun, Fan Yang, Wenbing Tao

In this paper, we present a second order spatial compatibility (SC^2) measure based method for efficient and robust point cloud registration (PCR), called SC^2-PCR.

Point Cloud Registration

Confidence Calibration for Intent Detection via Hyperspherical Space and Rebalanced Accuracy-Uncertainty Loss

no code implementations17 Mar 2022 Yantao Gong, Cao Liu, Fan Yang, Xunliang Cai, Guanglu Wan, Jiansong Chen, Weipeng Zhang, Houfeng Wang

Experiments on the open datasets verify that our model outperforms the existing calibration methods and achieves a significant improvement on the calibration metric.

Intent Detection

UniVIP: A Unified Framework for Self-Supervised Visual Pre-training

no code implementations CVPR 2022 Zhaowen Li, Yousong Zhu, Fan Yang, Wei Li, Chaoyang Zhao, Yingying Chen, Zhiyang Chen, Jiahao Xie, Liwei Wu, Rui Zhao, Ming Tang, Jinqiao Wang

Furthermore, our method can also exploit single-centric-object dataset such as ImageNet and outperforms BYOL by 2. 5% with the same pre-training epochs in linear probing, and surpass current self-supervised object detection methods on COCO dataset, demonstrating its universality and potential.

Image Classification object-detection +3

Learning from Attacks: Attacking Variational Autoencoder for Improving Image Classification

no code implementations11 Mar 2022 Jianzhang Zheng, Fan Yang, Hao Shen, Xuan Tang, Mingsong Chen, Liang Song, Xian Wei

We propose an algorithmic framework that leverages the advantages of the DNNs for data self-expression and task-specific predictions, to improve image classification.

Classification Image Classification

SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation

1 code implementation ICLR 2022 Cong Guo, Yuxian Qiu, Jingwen Leng, Xiaotian Gao, Chen Zhang, Yunxin Liu, Fan Yang, Yuhao Zhu, Minyi Guo

This paper proposes an on-the-fly DFQ framework with sub-second quantization time, called SQuant, which can quantize networks on inference-only devices with low computation and memory requirements.

Data Free Quantization

Learning Optical Flow with Adaptive Graph Reasoning

1 code implementation8 Feb 2022 Ao Luo, Fan Yang, Kunming Luo, Xin Li, Haoqiang Fan, Shuaicheng Liu

Our key idea is to decouple the context reasoning from the matching procedure, and exploit scene information to effectively assist motion estimation by learning to reason over the adaptive graph.

Motion Estimation Optical Flow Estimation +1

A comprehensive benchmark analysis for sand dust image reconstruction

no code implementations7 Feb 2022 Yazhong Si, Fan Yang, Ya Guo, Wei zhang, Yipu Yang

In this paper, we presented a comprehensive perceptual study and analysis of real-world sand dust images, then constructed a Sand-dust Image Reconstruction Benchmark (SIRB) for training Convolutional Neural Networks (CNNs) and evaluating algorithms performance.

Image Enhancement Image Reconstruction

Do Smart Glasses Dream of Sentimental Visions? Deep Emotionship Analysis for Eyewear Devices

1 code implementation24 Jan 2022 Yingying Zhao, Yuhu Chang, Yutian Lu, Yujiang Wang, Mingzhi Dong, Qin Lv, Robert P. Dick, Fan Yang, Tun Lu, Ning Gu, Li Shang

Experimental studies with 20 participants demonstrate that, thanks to the emotionship awareness, EMOShip not only achieves superior emotion recognition accuracy over existing methods (80. 2% vs. 69. 4%), but also provides a valuable understanding of the cause of emotions.

Emotion Recognition

BBA-net: A bi-branch attention network for crowd counting

no code implementations22 Jan 2022 Yi Hou, Chengyang Li, Fan Yang, Cong Ma, Liping Zhu, Yuan Li, Huizhu Jia, Xiaodong Xie

Our method can integrate the pedestrian's head and body information to enhance the feature expression ability of the density map.

Crowd Counting

SC2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration

no code implementations CVPR 2022 Zhi Chen, Kun Sun, Fan Yang, Wenbing Tao

In this paper, we present a second order spatial compatibility (SC^2) measure based method for efficient and robust point cloud registration (PCR), called SC^2-PCR.

Point Cloud Registration

Multimodal Dynamics: Dynamical Fusion for Trustworthy Multimodal Classification

1 code implementation CVPR 2022 Zongbo Han, Fan Yang, Junzhou Huang, Changqing Zhang, Jianhua Yao

To the best of our knowledge, this is the first work to jointly model both feature and modality variation for different samples to provide trustworthy fusion in multi-modal classification.

Informativeness Medical Diagnosis +1

DetarNet: Decoupling Translation and Rotation by Siamese Network for Point Cloud Registration

1 code implementation28 Dec 2021 Zhi Chen, Fan Yang, Wenbing Tao

In this paper, we propose a neural network named DetarNet to decouple the translation $t$ and rotation $R$, so as to overcome the performance degradation due to their mutual interference in point cloud registration.

Point Cloud Registration Translation

Neural Born Iteration Method For Solving Inverse Scattering Problems: 2D Cases

no code implementations18 Dec 2021 Tao Shan, Zhichao Lin, Xiaoqian Song, Maokun Li, Fan Yang, Shenheng Xu

In this paper, we propose the neural Born iteration method (NeuralBIM) for solving 2D inverse scattering problems (ISPs) by drawing on the scheme of physics-informed supervised residual learning (PhiSRL) to emulate the computing process of the traditional Born iteration method (TBIM).

A Simple Single-Scale Vision Transformer for Object Localization and Instance Segmentation

1 code implementation17 Dec 2021 Wuyang Chen, Xianzhi Du, Fan Yang, Lucas Beyer, Xiaohua Zhai, Tsung-Yi Lin, Huizhong Chen, Jing Li, Xiaodan Song, Zhangyang Wang, Denny Zhou

In this paper, we comprehensively study three architecture design choices on ViT -- spatial reduction, doubled channels, and multiscale features -- and demonstrate that a vanilla ViT architecture can fulfill this goal without handcrafting multiscale features, maintaining the original ViT design philosophy.

Image Classification Instance Segmentation +5

NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion

1 code implementation24 Nov 2021 Chenfei Wu, Jian Liang, Lei Ji, Fan Yang, Yuejian Fang, Daxin Jiang, Nan Duan

To cover language, image, and video at the same time for different scenarios, a 3D transformer encoder-decoder framework is designed, which can not only deal with videos as 3D data but also adapt to texts and images as 1D and 2D data, respectively.

Text to image generation Text-to-Image Generation +3

Towards Privacy-Preserving Affect Recognition: A Two-Level Deep Learning Architecture

no code implementations14 Nov 2021 Jimiama M. Mase, Natalie Leesakul, Fan Yang, Grazziela P. Figueredo, Mercedes Torres Torres

Possible solutions to protect the privacy of users and avoid misuse of their identities are to: (1) extract anonymised facial features, namely action units (AU) from a database of images, discard the images and use AUs for processing and training, and (2) federated learning (FL) i. e. process raw images in users' local machines (local processing) and send the locally trained models to the main processing machine for aggregation (central processing).

Federated Learning Privacy Preserving

Defense Against Explanation Manipulation

no code implementations8 Nov 2021 Ruixiang Tang, Ninghao Liu, Fan Yang, Na Zou, Xia Hu

Explainable machine learning attracts increasing attention as it improves transparency of models, which is helpful for machine learning to be trusted in real applications.

Adversarial Attack BIG-bench Machine Learning

Generalized Demographic Parity for Group Fairness

no code implementations ICLR 2022 Zhimeng Jiang, Xiaotian Han, Chao Fan, Fan Yang, Ali Mostafavi, Xia Hu

We show the understanding of GDP from the probability perspective and theoretically reveal the connection between GDP regularizer and adversarial debiasing.

Fairness

EXACT: Scalable Graph Neural Networks Training via Extreme Activation Compression

no code implementations ICLR 2022 Zirui Liu, Kaixiong Zhou, Fan Yang, Li Li, Rui Chen, Xia Hu

Based on the implementation, we propose a memory-efficient framework called ``EXACT'', which for the first time demonstrate the potential and evaluate the feasibility of training GNNs with compressed activations.

Graph Learning

Causal-TGAN: Causally-Aware Synthetic Tabular Data Generative Adversarial Network

no code implementations29 Sep 2021 Bingyang Wen, Yupeng Cao, Fan Yang, Koduvayur Subbalakshmi, Rajarathnam Chandramouli

The flexibility of this architecture is its capability to support different types of expert knowledge (e. g., complete or partial) about the causal nature of the underlying phenomenon.

Image Generation

LODE: Deep Local Deblurring and A New Benchmark

1 code implementation19 Sep 2021 Zerun Wang, Liuyu Xiang, Fan Yang, Jinzhao Qian, Jie Hu, Haidong Huang, Jungong Han, Yuchen Guo, Guiguang Ding

While recent deep deblurring algorithms have achieved remarkable progress, most existing methods focus on the global deblurring problem, where the image blur mostly arises from severe camera shake.

Deblurring

Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss

2 code implementations9 Sep 2021 Xing Cheng, Hezheng Lin, Xiangyu Wu, Fan Yang, Dong Shen

In this paper, we propose a multi-stream Corpus Alignment network with single gate Mixture-of-Experts (CAMoE) and a novel Dual Softmax Loss (DSL) to solve the two heterogeneity.

Ranked #5 on Video Retrieval on ActivityNet (using extra training data)

Retrieval Text Retrieval +1

LinEasyBO: Scalable Bayesian Optimization Approach for Analog Circuit Synthesis via One-Dimensional Subspaces

no code implementations1 Sep 2021 Shuhan Zhang, Fan Yang, Changhao Yan, Dian Zhou, Xuan Zeng

A large body of literature has proved that the Bayesian optimization framework is especially efficient and effective in analog circuit synthesis.

Actuarial-consistency and two-step actuarial valuations: a new paradigm to insurance valuation

no code implementations30 Aug 2021 Karim Barigou, Daniël Linders, Fan Yang

This paper introduces new valuation schemes called actuarial-consistent valuations for insurance liabilities which depend on both financial and actuarial risks, which imposes that all actuarial risks are priced via standard actuarial principles.

Adaptive Label Smoothing To Regularize Large-Scale Graph Training

no code implementations30 Aug 2021 Kaixiong Zhou, Ninghao Liu, Fan Yang, Zirui Liu, Rui Chen, Li Li, Soo-Hyun Choi, Xia Hu

Graph neural networks (GNNs), which learn the node representations by recursively aggregating information from its neighbors, have become a predominant computational tool in many domains.

Node Clustering

Efficient Visual Recognition with Deep Neural Networks: A Survey on Recent Advances and New Directions

no code implementations30 Aug 2021 Yang Wu, Dingheng Wang, Xiaotong Lu, Fan Yang, Guoqi Li, Weisheng Dong, Jianbo Shi

Visual recognition is currently one of the most important and active research areas in computer vision, pattern recognition, and even the general field of artificial intelligence.

RAIN: Reinforced Hybrid Attention Inference Network for Motion Forecasting

no code implementations ICCV 2021 Jiachen Li, Fan Yang, Hengbo Ma, Srikanth Malla, Masayoshi Tomizuka, Chiho Choi

Motion forecasting plays a significant role in various domains (e. g., autonomous driving, human-robot interaction), which aims to predict future motion sequences given a set of historical observations.

Motion Forecasting Trajectory Prediction

Opinion Prediction with User Fingerprinting

1 code implementation RANLP 2021 Kishore Tumarada, Yifan Zhang, Fan Yang, Eduard Dragut, Omprakash Gnawali, Arjun Mukherjee

Experimental results show novel insights that were previously unknown such as better predictions for an increase in dynamic history length, the impact of the nature of the article on performance, thereby laying the foundation for further research.

Sentiment Analysis Time Series

An Efficient Asynchronous Batch Bayesian Optimization Approach for Analog Circuit Synthesis

no code implementations28 Jun 2021 Shuhan Zhang, Fan Yang, Dian Zhou, Xuan Zeng

A new strategy is proposed to better balance the exploration and exploitation and guarantee the diversity of the query points.

An Efficient Batch Constrained Bayesian Optimization Approach for Analog Circuit Synthesis via Multi-objective Acquisition Ensemble

no code implementations28 Jun 2021 Shuhan Zhang, Fan Yang, Changhao Yan, Dian Zhou, Xuan Zeng

After achieving the first feasible point, we favor the feasible region by adopting a specially designed penalization term to the acquisition function ensemble.

A Scalable 256-Elements E-Band Phased-Array Transceiver for Broadband Communication

no code implementations20 Jun 2021 Xu Li, Wenyao Zhai, Morris Repeta, Hua Cai, Tyler Ross, Kimia Ansari, Sam Tiller, Hari Krishna Pothula, Dong Liang, Fan Yang, Yibo Lyu, Songlin Shuai, Guangjian Wang, Wen Tong

For E-band wireless communications, a high gain steerable antenna with sub-arrays is desired to reduce the implementation complexity.

Probabilistic Model Distillation for Semantic Correspondence

1 code implementation CVPR 2021 Xin Li, Deng-Ping Fan, Fan Yang, Ao Luo, Hong Cheng, Zicheng Liu

We address this problem with the use of a novel Probabilistic Model Distillation (PMD) approach which transfers knowledge learned by a probabilistic teacher model on synthetic data to a static student model with the use of unlabeled real image pairs.

Representation Learning Semantic correspondence

Model-Based Counterfactual Synthesizer for Interpretation

no code implementations16 Jun 2021 Fan Yang, Sahan Suresh Alva, Jiahao Chen, Xia Hu

To address these limitations, we propose a Model-based Counterfactual Synthesizer (MCS) framework for interpreting machine learning models.

Inductive Bias

From Paraphrasing to Semantic Parsing: Unsupervised Semantic Parsing via Synchronous Semantic Decoding

no code implementations ACL 2021 Shan Wu, Bo Chen, Chunlei Xin, Xianpei Han, Le Sun, Weipeng Zhang, Jiansong Chen, Fan Yang, Xunliang Cai

During synchronous decoding: the utterance paraphrasing is constrained by the structure of the logical form, therefore the canonical utterance can be paraphrased controlledly; the semantic decoding is guided by the semantics of the canonical utterance, therefore its logical form can be generated unsupervisedly.

Unsupervised semantic parsing

CAT: Cross Attention in Vision Transformer

1 code implementation10 Jun 2021 Hezheng Lin, Xing Cheng, Xiangyu Wu, Fan Yang, Dong Shen, Zhongyuan Wang, Qing Song, Wei Yuan

In this paper, we propose a new attention mechanism in Transformer termed Cross Attention, which alternates attention inner the image patch instead of the whole image to capture local information and apply attention between image patches which are divided from single-channel feature maps capture global information.

MST: Masked Self-Supervised Transformer for Visual Representation

no code implementations NeurIPS 2021 Zhaowen Li, Zhiyang Chen, Fan Yang, Wei Li, Yousong Zhu, Chaoyang Zhao, Rui Deng, Liwei Wu, Rui Zhao, Ming Tang, Jinqiao Wang

More importantly, the masked tokens together with the remaining tokens are further recovered by a global image decoder, which preserves the spatial information of the image and is more friendly to the downstream dense prediction tasks.

Language Modelling Masked Language Modeling +3

Calibrating multi-dimensional complex ODE from noisy data via deep neural networks

no code implementations7 Jun 2021 Kexuan Li, Fangfang Wang, Ruiqi Liu, Fan Yang, Zuofeng Shang

Our method is able to recover the ODE system without being subject to the curse of dimensionality and complicated ODE structure.

ModelPS: An Interactive and Collaborative Platform for Editing Pre-trained Models at Scale

1 code implementation18 May 2021 Yuanming Li, Huaizheng Zhang, Shanshan Jiang, Fan Yang, Yonggang Wen, Yong Luo

AI engineering has emerged as a crucial discipline to democratize deep neural network (DNN) models among software developers with a diverse background.

CT-Net: Complementary Transfering Network for Garment Transfer with Arbitrary Geometric Changes

no code implementations CVPR 2021 Fan Yang, Guosheng Lin

Garment transfer shows great potential in realistic applications with the goal of transfering outfits across different people images.

GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions

1 code implementation30 Apr 2021 Chenfei Wu, Lun Huang, Qianxi Zhang, Binyang Li, Lei Ji, Fan Yang, Guillermo Sapiro, Nan Duan

Generating videos from text is a challenging task due to its high computational requirements for training and infinite possible answers for evaluation.

Video Generation

Mutual Graph Learning for Camouflaged Object Detection

1 code implementation CVPR 2021 Qiang Zhai, Xin Li, Fan Yang, Chenglizhao Chen, Hong Cheng, Deng-Ping Fan

Automatically detecting/segmenting object(s) that blend in with their surroundings is difficult for current models.

Graph Learning object-detection +1

Superresolving second-order correlation imaging using synthesized colored noise speckles

no code implementations11 Feb 2021 Zheng Li, Xiaoyu Nie, Fan Yang, Xiangpei Liu, Dongyu Liu, Xiaolong Dong, Xingchen Zhao, Tao Peng, M. Suhail Zubairy, Marlan O. Scully

We present a novel method to synthesize non-trivial speckles that can enable superresolving second-order correlation imaging.

Optics Image and Video Processing

Cascade Network with Guided Loss and Hybrid Attention for Finding Good Correspondences

1 code implementation31 Jan 2021 Zhi Chen, Fan Yang, Wenbing Tao

We then propose a hybrid attention block to extract feature, which integrates the Bayesian attentive context normalization (BACN) and channel-wise attention (CA).

Generative Counterfactuals for Neural Networks via Attribute-Informed Perturbation

no code implementations18 Jan 2021 Fan Yang, Ninghao Liu, Mengnan Du, Xia Hu

With the wide use of deep neural networks (DNN), model interpretability has become a critical concern, since explainable decisions are preferred in high-stake scenarios.

Possible evidence of hydrogen emission in the first-overtone and multi-mode RR Lyrae variables

no code implementations24 Dec 2020 Xiao-Wei Duan, Xiao-Dian Chen, Li-Cai Deng, Fan Yang, Chao Liu, Anupam Bhardwaj, Hua-Wei Zhang

The nature of shock waves in non-fundamental mode RR Lyrae stars remains a mystery because of limited spectroscopic observations.

Solar and Stellar Astrophysics

A Polynomial Roth Theorem for Corners in Finite Fields

no code implementations21 Dec 2020 Rui Han, Michael T Lacey, Fan Yang

We prove a Roth type theorem for polynomial corners in the finite field setting.

Classical Analysis and ODEs Combinatorics Number Theory

Pattern-aware Data Augmentation for Query Rewriting in Voice Assistant Systems

no code implementations21 Dec 2020 Yunmo Chen, Sixing Lu, Fan Yang, Xiaojiang Huang, Xing Fan, Chenlei Guo

Query rewriting (QR) systems are widely used to reduce the friction caused by errors in a spoken language understanding pipeline.

Data Augmentation Friction +1

Multi-Aspect Sentiment Analysis with Latent Sentiment-Aspect Attribution

no code implementations15 Dec 2020 Yifan Zhang, Fan Yang, Marjan Hosseinia, Arjun Mukherjee

In this paper, we introduce a new framework called the sentiment-aspect attribution module (SAAM).

Sentiment Analysis

Bayesian Multi-type Mean Field Multi-agent Imitation Learning

no code implementations NeurIPS 2020 Fan Yang, Alina Vereshchaka, Changyou Chen, Wen Dong

We demonstrate the performance of our algorithm through benchmarking with three state-of-the-art multi-agent imitation learning algorithms on several tasks, including solving a multi-agent traffic optimization problem in a real-world transportation network.

Imitation Learning

PAMS: Quantized Super-Resolution via Parameterized Max Scale

1 code implementation ECCV 2020 Huixia Li, Chenqian Yan, Shaohui Lin, Xiawu Zheng, Yuchao Li, Baochang Zhang, Fan Yang, Rongrong Ji

Specifically, most state-of-the-art SR models without batch normalization have a large dynamic quantization range, which also serves as another cause of performance drop.

Quantization Super-Resolution +1

Analysis of Information Transfer from Heterogeneous Sources via Precise High-dimensional Asymptotics

no code implementations22 Oct 2020 Fan Yang, Hongyang R. Zhang, Sen Wu, Weijie J. Su, Christopher Ré

A fundamental question in transfer learning is whether combining the data of both tasks works better than using only the target task's data (equivalently, whether a "positive information transfer" happens).

Multi-Task Learning text-classification +1

Linear-time Temporal Logic with Team Semantics: Expressivity and Complexity

no code implementations7 Oct 2020 Jonni Virtema, Jana Hofmann, Bernd Finkbeiner, Juha Kontinen, Fan Yang

We study the expressivity and complexity of model checking linear temporal logic with team semantics (TeamLTL).

Logic in Computer Science Computational Complexity F.4.1; D.2.4

Towards Fast, Accurate and Stable 3D Dense Face Alignment

3 code implementations ECCV 2020 Jianzhu Guo, Xiangyu Zhu, Yang Yang, Fan Yang, Zhen Lei, Stan Z. Li

Firstly, on the basis of a lightweight backbone, we propose a meta-joint optimization strategy to dynamically regress a small set of 3DMM parameters, which greatly enhances speed and accuracy simultaneously.

 Ranked #1 on 3D Face Reconstruction on Florence (Mean NME metric)

3D Face Modelling 3D Face Reconstruction +2

RelativeNAS: Relative Neural Architecture Search via Slow-Fast Learning

2 code implementations14 Sep 2020 Hao Tan, Ran Cheng, Shihua Huang, Cheng He, Changxiao Qiu, Fan Yang, Ping Luo

Despite the remarkable successes of Convolutional Neural Networks (CNNs) in computer vision, it is time-consuming and error-prone to manually design a CNN.

Keypoint Detection Neural Architecture Search +3

LaSOT: A High-quality Large-scale Single Object Tracking Benchmark

1 code implementation8 Sep 2020 Heng Fan, Hexin Bai, Liting Lin, Fan Yang, Peng Chu, Ge Deng, Sijia Yu, Harshit, Mingzhen Huang, Juehuan Liu, Yong Xu, Chunyuan Liao, Lin Yuan, Haibin Ling

The average video length of LaSOT is around 2, 500 frames, where each video contains various challenge factors that exist in real world video footage, such as the targets disappearing and re-appearing.

Object Tracking Visual Tracking

Cascade Graph Neural Networks for RGB-D Salient Object Detection

1 code implementation ECCV 2020 Ao Luo, Xin Li, Fan Yang, Zhicheng Jiao, Hong Cheng, Siwei Lyu

Current works either simply distill prior knowledge from the corresponding depth map for handling the RGB-image or blindly fuse color and geometric information to generate the coarse depth-aware representations, hindering the performance of RGB-D saliency detectors. In this work, we introduceCascade Graph Neural Networks(Cas-Gnn), a unified framework which is capable of comprehensively distilling and reasoning the mutual benefits between these two data sources through a set of cascade graphs, to learn powerful representations for RGB-D salient object detection.

object-detection RGB-D Salient Object Detection +2

PIC-Net: Point Cloud and Image Collaboration Network for Large-Scale Place Recognition

no code implementations3 Aug 2020 Yuheng Lu, Fan Yang, Fangping Chen, Don Xie

Place recognition is one of the hot research fields in automation technology and is still an open issue, Camera and Lidar are two mainstream sensors used in this task, Camera-based methods are easily affected by illumination and season changes, LIDAR cannot get the rich data as the image could , In this paper, we propose the PIC-Net (Point cloud and Image Collaboration Network), which use attention mechanism to fuse the features of image and point cloud, and mine the complementary information between the two.

Cascade Network with Guided Loss and Hybrid Attention for Two-view Geometry

no code implementations11 Jul 2020 Zhi Chen, Fan Yang, Wenbing Tao

We then propose a hybrid attention block to extract feature, which integrates the bayesian attentive context normalization (BACN) and channel-wise attention (CA).

An Embarrassingly Simple Approach for Trojan Attack in Deep Neural Networks

1 code implementation15 Jun 2020 Ruixiang Tang, Mengnan Du, Ninghao Liu, Fan Yang, Xia Hu

In this paper, we investigate a specific security problem called trojan attack, which aims to attack deployed DNN systems relying on the hidden trigger patterns inserted by malicious hackers.

Defending SVMs against Poisoning Attacks: the Hardness and DBSCAN Approach

no code implementations14 Jun 2020 Hu Ding, Fan Yang, Jiawei Huang

For the data sanitization defense, we link it to the intrinsic dimensionality of data; in particular, we provide a sampling theorem in doubling metrics for explaining the effectiveness of DBSCAN (as a density-based outlier removal method) for defending against poisoning attacks.

MSDU-net: A Multi-Scale Dilated U-net for Blur Detection

no code implementations5 Jun 2020 Fan Yang, Xiao Xiao

Blur detection is the separation of blurred and clear regions of an image, which is an important and challenging task in computer vision.

Image Segmentation Semantic Segmentation

Learning to Detect Head Movement in Unconstrained Remote Gaze Estimation in the Wild

no code implementations7 Apr 2020 Zhecan Wang, Jian Zhao, Cheng Lu, Han Huang, Fan Yang, Lianji Li, Yandong Guo

To better demonstrate the advantage of our methods, we further propose a new benchmark dataset with the most rich distribution of head-gaze combination reflecting real-world scenarios.

Gaze Estimation

XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation

2 code implementations3 Apr 2020 Yaobo Liang, Nan Duan, Yeyun Gong, Ning Wu, Fenfei Guo, Weizhen Qi, Ming Gong, Linjun Shou, Daxin Jiang, Guihong Cao, Xiaodong Fan, Ruofei Zhang, Rahul Agrawal, Edward Cui, Sining Wei, Taroon Bharti, Ying Qiao, Jiun-Hung Chen, Winnie Wu, Shuguang Liu, Fan Yang, Daniel Campos, Rangan Majumder, Ming Zhou

In this paper, we introduce XGLUE, a new benchmark dataset that can be used to train large-scale cross-lingual pre-trained models using multilingual and bilingual corpora and evaluate their performance across a diverse set of cross-lingual tasks.

Natural Language Understanding XLM-R

EvolveGraph: Multi-Agent Trajectory Prediction with Dynamic Relational Reasoning

no code implementations NeurIPS 2020 Jiachen Li, Fan Yang, Masayoshi Tomizuka, Chiho Choi

In this paper, we propose a generic trajectory forecasting framework (named EvolveGraph) with explicit relational structure recognition and prediction via latent interaction graphs among multiple heterogeneous, interactive agents.

Autonomous Driving Decision Making +2

Hybrid Graph Neural Networks for Crowd Counting

no code implementations31 Jan 2020 Ao Luo, Fan Yang, Xin Li, Dong Nie, Zhicheng Jiao, Shangchen Zhou, Hong Cheng

In this paper, we present a novel network structure called Hybrid Graph Neural Network (HyGnn) which targets to relieve the problem by interweaving the multi-scale features for crowd density as well as its auxiliary task (localization) together and performing joint reasoning over a graph.

Crowd Counting

Tricritical physics in two-dimensional $p$-wave superfluids

no code implementations16 Jan 2020 Fan Yang, Shao-Jian Jiang, Fei Zhou

When strong quantum fluctuations near resonance are taken into account, the line of continuous phase transitions terminates at two multicritical points near resonance, between which the transitions are expected to be first-order ones.

Quantum Gases

Relational State-Space Model for Stochastic Multi-Object Systems

no code implementations ICLR 2020 Fan Yang, Ling Chen, Fan Zhou, Yusong Gao, Wei Cao

Real-world dynamical systems often consist of multiple stochastic subsystems that interact with each other.

Time Series

Game Design for Eliciting Distinguishable Behavior

no code implementations NeurIPS 2019 Fan Yang, Liu Leqi, Yifan Wu, Zachary C. Lipton, Pradeep Ravikumar, William W. Cohen, Tom Mitchell

The ability to inferring latent psychological traits from human behavior is key to developing personalized human-interacting machine learning systems.

Dually Supervised Feature Pyramid for Object Detection and Segmentation

1 code implementation8 Dec 2019 Fan Yang, Cheng Lu, Yandong Guo, Longin Jan Latecki, Haibin Ling

Feature pyramid architecture has been broadly adopted in object detection and segmentation to deal with multi-scale problem.

object-detection Object Detection +1

Bayesian Optimization Approach for Analog Circuit Synthesis Using Neural Network

no code implementations1 Dec 2019 Shuhan Zhang, Wenlong Lyu, Fan Yang, Changhao Yan, Dian Zhou, Xuan Zeng

Bayesian optimization with Gaussian process as surrogate model has been successfully applied to analog circuit synthesis.

Detecting Unknown Behaviors by Pre-defined Behaviours: An Bayesian Non-parametric Approach

no code implementations25 Nov 2019 Jin Watanabe, Takatomi Kubo, Fan Yang, Kazushi Ikeda

An automatic mouse behavior recognition system can considerably reduce the workload of experimenters and facilitate the analysis process.

Using Panoramic Videos for Multi-person Localization and Tracking in a 3D Panoramic Coordinate

1 code implementation24 Nov 2019 Fan Yang, Feiran Li, Yang Wu, Sakriani Sakti, Satoshi Nakamura

3D panoramic multi-person localization and tracking are prominent in many applications, however, conventional methods using LiDAR equipment could be economically expensive and also computationally inefficient due to the processing of point cloud data.

 Ranked #1 on Multi-Object Tracking on MOT15_3D (using extra training data)

Multi-Object Tracking

TracKlinic: Diagnosis of Challenge Factors in Visual Tracking

no code implementations18 Nov 2019 Heng Fan, Fan Yang, Peng Chu, Lin Yuan, Haibin Ling

For the analysis component, given the tracking results on all sequences, it investigates the behavior of the tracker under each individual factor and generates the report automatically.

Visual Tracking

XDeep: An Interpretation Tool for Deep Neural Networks

1 code implementation4 Nov 2019 Fan Yang, Zijian Zhang, Haofan Wang, Yuening Li, Xia Hu

XDeep is an open-source Python package developed to interpret deep models for both practitioners and researchers.

A Hierarchical Mixture Density Network

no code implementations23 Oct 2019 Fan Yang, Jaymar Soriano, Takatomi Kubo, Kazushi Ikeda

One of the complicated relationships among three correlated variables could be a two-layer hierarchical many-to-many mapping.

TruNet: Short Videos Generation from Long Videos via Story-Preserving Truncation

no code implementations14 Oct 2019 Fan Yang, Xiao Liu, Dongliang He, Chuang Gan, Jian Wang, Chao Li, Fu Li, Shilei Wen

In this work, we introduce a new problem, named as {\em story-preserving long video truncation}, that requires an algorithm to automatically truncate a long-duration video into multiple short and attractive sub-videos with each one containing an unbroken story.

Highlight Detection Video Summarization

Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks

8 code implementations3 Oct 2019 Haofan Wang, Zifan Wang, Mengnan Du, Fan Yang, Zijian Zhang, Sirui Ding, Piotr Mardziel, Xia Hu

Recently, increasing attention has been drawn to the internal mechanisms of convolutional neural networks, and the reason why the network makes specific decisions.

Adversarial Attack Decision Making +1

Contextual Local Explanation for Black Box Classifiers

no code implementations2 Oct 2019 Zijian Zhang, Fan Yang, Haofan Wang, Xia Hu

We introduce a new model-agnostic explanation technique which explains the prediction of any classifier called CLE.

General Classification Image Classification

GLA-Net: An Attention Network with Guided Loss for Mismatch Removal

no code implementations28 Sep 2019 Zhi Chen, Fan Yang, Wenbing Tao

To establish the link between Fn-score and loss, we propose to guide the loss with the Fn-score directly.

Fairness in Deep Learning: A Computational Perspective

no code implementations23 Aug 2019 Mengnan Du, Fan Yang, Na Zou, Xia Hu

Deep learning is increasingly being used in high-stake decision making applications that affect individual lives.

Decision Making Fairness

Learning Credible Deep Neural Networks with Rationale Regularization

no code implementations13 Aug 2019 Mengnan Du, Ninghao Liu, Fan Yang, Xia Hu

Recent explainability related studies have shown that state-of-the-art DNNs do not always adopt correct evidences to make decisions.

text-classification Text Classification

Annotation-Free Cardiac Vessel Segmentation via Knowledge Transfer from Retinal Images

no code implementations26 Jul 2019 Fei Yu, Jie Zhao, Yanjun Gong, Zhi Wang, Yuxi Li, Fan Yang, Bin Dong, Quanzheng Li, Li Zhang

Segmenting coronary arteries is challenging, as classic unsupervised methods fail to produce satisfactory results and modern supervised learning (deep learning) requires manual annotation which is often time-consuming and can some time be infeasible.

Transfer Learning

Make Skeleton-based Action Recognition Model Smaller, Faster and Better

3 code implementations arXiv 2019 Fan Yang, Sakriani Sakti, Yang Wu, Satoshi Nakamura

Although skeleton-based action recognition has achieved great success in recent years, most of the existing methods may suffer from a large model size and slow execution speed.

Action Recognition Skeleton Based Action Recognition

Evaluating Explanation Without Ground Truth in Interpretable Machine Learning

no code implementations16 Jul 2019 Fan Yang, Mengnan Du, Xia Hu

Interpretable Machine Learning (IML) has become increasingly important in many real-world applications, such as autonomous cars and medical diagnosis, where explanations are significantly preferred to help people better understand how machine learning systems work and further enhance their trust towards systems.

BIG-bench Machine Learning Interpretable Machine Learning +1

XFake: Explainable Fake News Detector with Visualizations

no code implementations8 Jul 2019 Fan Yang, Shiva K. Pentyala, Sina Mohseni, Mengnan Du, Hao Yuan, Rhema Linder, Eric D. Ragan, Shuiwang Ji, Xia Hu

In this demo paper, we present the XFake system, an explainable fake news detector that assists end-users to identify news credibility.

Reconstructing Perceived Images from Brain Activity by Visually-guided Cognitive Representation and Adversarial Learning

no code implementations27 Jun 2019 Ziqi Ren, Jie Li, Xuetong Xue, Xin Li, Fan Yang, Zhicheng Jiao, Xinbo Gao

In addition, we introduce a novel three-stage learning approach which enables the (cognitive) encoder to gradually distill useful knowledge from the paired (visual) encoder during the learning process.

Image Reconstruction Knowledge Distillation +1