Search Results for author: Bin Yang

Found 168 papers, 57 papers with code

Part2Object: Hierarchical Unsupervised 3D Instance Segmentation

1 code implementation14 Jul 2024 Cheng Shi, Yulin Zhang, Bin Yang, Jiajin Tang, Yuexin Ma, Sibei Yang

By training Hi-Mask3D on the objects and object parts extracted from Part2Object, we achieve consistent and superior performance compared to state-of-the-art models in various settings, including unsupervised instance segmentation, data-efficient fine-tuning, and cross-dataset generalization.

Towards a General Time Series Anomaly Detector with Adaptive Bottlenecks and Dual Adversarial Decoders

no code implementations24 May 2024 Qichao Shentu, Beibu Li, Kai Zhao, Yang Shu, Zhongwen Rao, Lujia Pan, Bin Yang, Chenjuan Guo

The significant divergence of time series data across different domains presents two primary challenges in building such a general model: (1) meeting the diverse requirements of appropriate information bottlenecks tailored to different datasets in one unified model, and (2) enabling distinguishment between multiple normal and abnormal patterns, both are crucial for effective anomaly detection in various target scenarios.

Anomaly Detection Time Series +1

ROSE: Register Assisted General Time Series Forecasting with Decomposed Frequency Learning

no code implementations24 May 2024 Yihang Wang, Yuying Qiu, Peng Chen, Kai Zhao, Yang Shu, Zhongwen Rao, Lujia Pan, Bin Yang, Chenjuan Guo

Enabling general time series forecasting faces two challenges: how to obtain unified representations from multi-domian time series data, and how to capture domain-specific features from time series data across various domains for adaptive transfer in downstream tasks.

Time Series Time Series Forecasting

A Lost Opportunity for Vision-Language Models: A Comparative Study of Online Test-time Adaptation for Vision-Language Models

1 code implementation23 May 2024 Mario Döbler, Robert A. Marsden, Tobias Raichle, Bin Yang

Through a systematic exploration of prompt-based techniques and existing test-time adaptation methods, the study aims to enhance the adaptability and robustness of vision-language models in diverse real-world scenarios.

Image Classification Prompt Engineering +1

A Survey on Diffusion Models for Time Series and Spatio-Temporal Data

1 code implementation29 Apr 2024 Yiyuan Yang, Ming Jin, Haomin Wen, Chaoli Zhang, Yuxuan Liang, Lintao Ma, Yi Wang, Chenghao Liu, Bin Yang, Zenglin Xu, Jiang Bian, Shirui Pan, Qingsong Wen

Conditioned models, on the other hand, utilize extra information to enhance performance and are similarly divided for both predictive and generative tasks.

Anomaly Detection Imputation +1

Flood Data Analysis on SpaceNet 8 Using Apache Sedona

no code implementations28 Apr 2024 Yanbing Bai, Zihao Yang, Jinze Yu, Rui-Yang Ju, Bin Yang, Erick Mas, Shunichi Koshimura

This platform aims to enhance the efficiency of error analysis, a critical aspect of improving flood damage detection accuracy.

A Unified Replay-based Continuous Learning Framework for Spatio-Temporal Prediction on Streaming Data

no code implementations23 Apr 2024 Hao Miao, Yan Zhao, Chenjuan Guo, Bin Yang, Kai Zheng, Feiteng Huang, Jiandong Xie, Christian S. Jensen

The widespread deployment of wireless and mobile devices results in a proliferation of spatio-temporal data that is used in applications, e. g., traffic prediction, human mobility mining, and air quality prediction, where spatio-temporal prediction is often essential to enable safety, predictability, or reliability.

Data Augmentation Traffic Prediction

QCore: Data-Efficient, On-Device Continual Calibration for Quantized Models -- Extended Version

1 code implementation22 Apr 2024 David Campos, Bin Yang, Tung Kieu, Miao Zhang, Chenjuan Guo, Christian S. Jensen

The first difficulty in enabling continual calibration on the edge is that the full training data may be too large and thus not always available on edge devices.

Continual Learning

TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods

1 code implementation29 Mar 2024 Xiangfei Qiu, Jilin Hu, Lekui Zhou, Xingjian Wu, Junyang Du, Buang Zhang, Chenjuan Guo, Aoying Zhou, Christian S. Jensen, Zhenli Sheng, Bin Yang

Next, we employ TFB to perform a thorough evaluation of 21 Univariate Time Series Forecasting (UTSF) methods on 8, 068 univariate time series and 14 Multivariate Time Series Forecasting (MTSF) methods on 25 datasets.

Benchmarking Multivariate Time Series Forecasting +2

Dual-modal Prior Semantic Guided Infrared and Visible Image Fusion for Intelligent Transportation System

no code implementations24 Mar 2024 Jing Li, Lu Bai, Bin Yang, Chang Li, Lingfei Ma, Lixin Cui, Edwin R. Hancock

Therefore, we propose a novel prior semantic guided image fusion method based on the dual-modality strategy, improving the performance of IVF in ITS.

Infrared And Visible Image Fusion Semantic Segmentation

Position: What Can Large Language Models Tell Us about Time Series Analysis

no code implementations5 Feb 2024 Ming Jin, Yifan Zhang, Wei Chen, Kexin Zhang, Yuxuan Liang, Bin Yang, Jindong Wang, Shirui Pan, Qingsong Wen

Time series analysis is essential for comprehending the complexities inherent in various realworld systems and applications.

Decision Making Position +3

Shallow-Deep Collaborative Learning for Unsupervised Visible-Infrared Person Re-Identification

1 code implementation CVPR 2024 Bin Yang, Jun Chen, Mang Ye

Unsupervised visible-infrared person re-identification (US-VI-ReID) centers on learning a cross-modality retrieval model without labels reducing the reliance on expensive cross-modality manual annotation.

Collaborative Ranking Contrastive Learning +1

AI-driven projection tomography with multicore fibre-optic cell rotation

1 code implementation12 Dec 2023 Jiawei Sun, Bin Yang, Nektarios Koukourakis, Jochen Guck, Juergen W. Czarske

The performance of the proposed cell rotation tomography approach is validated through the three-dimensional reconstruction of cell phantoms and HL60 human cancer cells.

Calibration-free online test-time adaptation for electroencephalography motor imagery decoding

1 code implementation30 Nov 2023 Martin Wimpff, Mario Döbler, Bin Yang

Providing a promising pathway to link the human brain with external devices, Brain-Computer Interfaces (BCIs) have seen notable advancements in decoding capabilities, primarily driven by increasingly sophisticated techniques, especially deep learning.

EEG Motor Imagery +2

Graph Representation Learning for Infrared and Visible Image Fusion

no code implementations1 Nov 2023 Jing Li, Lu Bai, Bin Yang, Chang Li, Lingfei Ma, Edwin R. Hancock

Then, GCNs are performed on the concatenate intra-modal NLss features of infrared and visible images, which can explore the cross-domain NLss of inter-modal to reconstruct the fused image.

Graph Representation Learning Infrared And Visible Image Fusion

EEG motor imagery decoding: A framework for comparative analysis with channel attention mechanisms

2 code implementations17 Oct 2023 Martin Wimpff, Leonardo Gizzi, Jan Zerfowski, Bin Yang

The objective of this study is to investigate the application of various channel attention mechanisms within the domain of brain-computer interface (BCI) for motor imagery decoding.

EEG Motor Imagery

AdaRec: Adaptive Sequential Recommendation for Reinforcing Long-term User Engagement

no code implementations6 Oct 2023 Zhenghai Xue, Qingpeng Cai, Tianyou Zuo, Bin Yang, Lantao Hu, Peng Jiang, Kun Gai, Bo An

One challenge in large-scale online recommendation systems is the constant and complicated changes in users' behavior patterns, such as interaction rates and retention tendencies.

Reinforcement Learning (RL) Sequential Recommendation

Origin-Destination Travel Time Oracle for Map-based Services

no code implementations6 Jul 2023 Yan Lin, Huaiyu Wan, Jilin Hu, Shengnan Guo, Bin Yang, Youfang Lin, Christian S. Jensen

Given an origin (O), a destination (D), and a departure time (T), an Origin-Destination (OD) travel time oracle~(ODT-Oracle) returns an estimate of the time it takes to travel from O to D when departing at T. ODT-Oracles serve important purposes in map-based services.

Travel Time Estimation

Weight Compander: A Simple Weight Reparameterization for Regularization

no code implementations29 Jun 2023 Rinor Cakaj, Jens Mehnert, Bin Yang

Large weights in deep neural networks are a sign of a more complex network that is overfitted to the training data.

Decision Making

Spectral Batch Normalization: Normalization in the Frequency Domain

no code implementations29 Jun 2023 Rinor Cakaj, Jens Mehnert, Bin Yang

However, we show experimentally that, despite the approximate additive penalty of BN, feature maps in deep neural networks (DNNs) tend to explode at the beginning of the network and that feature maps of DNNs contain large values during the whole training.

A Semi-Paired Approach For Label-to-Image Translation

no code implementations23 Jun 2023 George Eskandar, Shuai Zhang, Mohamed Abdelsamad, Mark Youssef, Diandian Guo, Bin Yang

Data efficiency, or the ability to generalize from a few labeled data, remains a major challenge in deep learning.

Image-to-Image Translation Translation

A Crystal-Specific Pre-Training Framework for Crystal Material Property Prediction

no code implementations8 Jun 2023 Haomin Yu, Yanru Song, Jilin Hu, Chenjuan Guo, Bin Yang

To overcome these challenges, we propose the crystal-specific pre-training framework for learning crystal representations with self-supervision.

Attribute Physical Simulations +2

Universal Test-time Adaptation through Weight Ensembling, Diversity Weighting, and Prior Correction

1 code implementation1 Jun 2023 Robert A. Marsden, Mario Döbler, Bin Yang

To tackle the problem of universal TTA, we identify and highlight several challenges a self-training based method has to deal with: 1) model bias and the occurrence of trivial solutions when performing entropy minimization on varying sequence lengths with and without multiple domain shifts, 2) loss of generalization which exacerbates the adaptation to multiple domain shifts and the occurrence of catastrophic forgetting, and 3) performance degradation due to shifts in class prior.

Diversity Test-time Adaptation

Urban-StyleGAN: Learning to Generate and Manipulate Images of Urban Scenes

no code implementations16 May 2023 George Eskandar, Youssef Farag, Tarun Yenamandra, Daniel Cremers, Karim Guirguis, Bin Yang

Moreover, we employ an unsupervised latent exploration algorithm in the $\mathcal{S}$-space of the generator and show that it is more efficient than the conventional $\mathcal{W}^{+}$-space in controlling the image content.

Autonomous Driving Disentanglement +2

Towards Pragmatic Semantic Image Synthesis for Urban Scenes

1 code implementation16 May 2023 George Eskandar, Diandian Guo, Karim Guirguis, Bin Yang

Second, in contrast to previous works which employ one discriminator that overfits the target domain semantic distribution, we employ a discriminator for the whole image and multiscale discriminators on the image patches.

Autonomous Driving Image Generation

NIFF: Alleviating Forgetting in Generalized Few-Shot Object Detection via Neural Instance Feature Forging

no code implementations CVPR 2023 Karim Guirguis, Johannes Meier, George Eskandar, Matthias Kayser, Bin Yang, Juergen Beyerer

Our contribution is three-fold: (1) we design a standalone lightweight generator with (2) class-wise heads (3) to generate and replay diverse instance-level base features to the RoI head while finetuning on the novel data.

Data-free Knowledge Distillation Few-Shot Object Detection +2

LightTS: Lightweight Time Series Classification with Adaptive Ensemble Distillation -- Extended Version

1 code implementation24 Feb 2023 David Campos, Miao Zhang, Bin Yang, Tung Kieu, Chenjuan Guo, Christian S. Jensen

First, we propose adaptive ensemble distillation that assigns adaptive weights to different base models such that their varying classification capabilities contribute purposefully to the training of the lightweight model.

Classification Decision Making +4

Reinforcing User Retention in a Billion Scale Short Video Recommender System

no code implementations3 Feb 2023 Qingpeng Cai, Shuchang Liu, Xueliang Wang, Tianyou Zuo, Wentao Xie, Bin Yang, Dong Zheng, Peng Jiang, Kun Gai

In this paper, we choose reinforcement learning methods to optimize the retention as they are designed to maximize the long-term performance.

Recommendation Systems reinforcement-learning +1

LSDM: Long-Short Diffeomorphic Motion for Weakly-Supervised Ultrasound Landmark Tracking

no code implementations11 Jan 2023 Zhihua Liu, Bin Yang, Yan Shen, Xuejun Ni, Huiyu Zhou

In this paper, we propose a long-short diffeomorphic motion network, which is a multi-task framework with a learnable deformation prior to search for the plausible deformation of landmark.

Landmark Tracking

Towards Grand Unified Representation Learning for Unsupervised Visible-Infrared Person Re-Identification

1 code implementation ICCV 2023 Bin Yang, Jun Chen, Mang Ye

The grand unified representation lies in two aspects: 1) GUR adopts a bottom-up domain learning strategy with a cross-memory association embedding module to explore the information of hierarchical domains, i. e., intra-camera, inter-camera, and inter-modality domains, learning a unified and robust representation against hierarchical discrepancy.

Person Re-Identification Representation Learning

A Pattern Discovery Approach to Multivariate Time Series Forecasting

no code implementations20 Dec 2022 Yunyao Cheng, Chenjuan Guo, KaiXuan Chen, Kai Zhao, Bin Yang, Jiandong Xie, Christian S. Jensen, Feiteng Huang, Kai Zheng

To capture the temporal and multivariate correlations among subsequences, we design a pattern discovery model, that constructs correlations via diverse pattern functions.

Diversity Multivariate Time Series Forecasting +1

FLAG3D: A 3D Fitness Activity Dataset with Language Instruction

1 code implementation CVPR 2023 Yansong Tang, Jinpeng Liu, Aoyang Liu, Bin Yang, Wenxun Dai, Yongming Rao, Jiwen Lu, Jie zhou, Xiu Li

With the continuously thriving popularity around the world, fitness activity analytic has become an emerging research topic in computer vision.

Action Generation Action Recognition +2

AutoPINN: When AutoML Meets Physics-Informed Neural Networks

no code implementations8 Dec 2022 Xinle Wu, Dalin Zhang, Miao Zhang, Chenjuan Guo, Shuai Zhao, Yi Zhang, Huai Wang, Bin Yang

We then propose a resource-aware search strategy to explore the search space to find the best PINN model under different resource constraints.


Joint Neural Architecture and Hyperparameter Search for Correlated Time Series Forecasting

no code implementations29 Nov 2022 Xinle Wu, Dalin Zhang, Miao Zhang, Chenjuan Guo, Bin Yang, Christian S. Jensen

To overcome these limitations, we propose SEARCH, a joint, scalable framework, to automatically devise effective CTS forecasting models.

Correlated Time Series Forecasting Time Series

Robust Mean Teacher for Continual and Gradual Test-Time Adaptation

1 code implementation CVPR 2023 Mario Döbler, Robert A. Marsden, Bin Yang

We demonstrate the effectiveness of our proposed method 'robust mean teacher' (RMT) on the continual and gradual corruption benchmarks CIFAR10C, CIFAR100C, and Imagenet-C. We further consider ImageNet-R and propose a new continual DomainNet-126 benchmark.

Contrastive Learning Test-time Adaptation

Variation-based Cause Effect Identification

1 code implementation22 Nov 2022 Mohamed Amine ben Salem, Karim Said Barsim, Bin Yang

In the causal direction, such variations are expected to have no impact on the effect generation mechanism.

Causal Discovery

Prompt Tuning for Parameter-efficient Medical Image Segmentation

2 code implementations16 Nov 2022 Marc Fischer, Alexander Bartler, Bin Yang

As such, fine-tuning a model to a downstream task in a parameter-efficient but effective way, e. g. for a new set of classes in the case of semantic segmentation, is of increasing importance.

Image Segmentation Medical Image Segmentation +2

On-Board Pedestrian Trajectory Prediction Using Behavioral Features

no code implementations21 Oct 2022 Phillip Czech, Markus Braun, Ulrich Kreßel, Bin Yang

This paper presents a novel approach to pedestrian trajectory prediction for on-board camera systems, which utilizes behavioral features of pedestrians that can be inferred from visual observations.

Pedestrian Trajectory Prediction Trajectory Prediction

Augmented Dual-Contrastive Aggregation Learning for Unsupervised Visible-Infrared Person Re-Identification

1 code implementation ACM MM 2022 Bin Yang, Mang Ye, Jun Chen, Zesen Wu

Visible infrared person re-identification (VI-ReID) aims at searching out the corresponding infrared (visible) images from a gallery set captured by other spectrum cameras.

Contrastive Learning Person Re-Identification

Towards Discriminative and Transferable One-Stage Few-Shot Object Detectors

no code implementations11 Oct 2022 Karim Guirguis, Mohamed Abdelsamad, George Eskandar, Ahmed Hendawy, Matthias Kayser, Bin Yang, Juergen Beyerer

We make the observation that the large gap in performance between two-stage and one-stage FSODs are mainly due to their weak discriminability, which is explained by a small post-fusion receptive field and a small number of foreground samples in the loss function.

Few-Shot Object Detection object-detection

Deep Feature Selection Using a Novel Complementary Feature Mask

no code implementations25 Sep 2022 Yiwen Liao, Jochen Rivoir, Raphaël Latty, Bin Yang

However, most existing feature selection approaches, especially deep-learning-based, often focus on the features with great importance scores only but neglect those with less importance scores during training as well as the order of important candidate features.

Benchmarking feature selection

CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement

2 code implementations22 Sep 2022 Sherif Abdulatif, Ruizhe Cao, Bin Yang

Rather than focusing exclusively on the speech denoising task, we extend this work to address the dereverberation and super-resolution tasks.

Audio Super-Resolution Automatic Speech Recognition +9

A Comparative Study on Unsupervised Anomaly Detection for Time Series: Experiments and Analysis

no code implementations10 Sep 2022 Yan Zhao, Liwei Deng, Xuanhao Chen, Chenjuan Guo, Bin Yang, Tung Kieu, Feiteng Huang, Torben Bach Pedersen, Kai Zheng, Christian S. Jensen

The continued digitization of societal processes translates into a proliferation of time series data that cover applications such as fraud detection, intrusion detection, and energy management, where anomaly detection is often essential to enable reliability and safety.

Diversity energy management +6

Design Automation for Fast, Lightweight, and Effective Deep Learning Models: A Survey

no code implementations22 Aug 2022 Dalin Zhang, KaiXuan Chen, Yan Zhao, Bin Yang, Lina Yao, Christian S. Jensen

A key challenge is that while the application of deep models often incurs substantial memory and computational costs, edge devices typically offer only very limited storage and computational capabilities that may vary substantially across devices.

Edge-computing Model Compression +1

Introducing Intermediate Domains for Effective Self-Training during Test-Time

1 code implementation16 Aug 2022 Robert A. Marsden, Mario Döbler, Bin Yang

In this work, we address two problems that exist when applying self-training in the setting of test-time adaptation.

Scene Segmentation Style Transfer +2

Continual Unsupervised Domain Adaptation for Semantic Segmentation using a Class-Specific Transfer

no code implementations12 Aug 2022 Robert A. Marsden, Felix Wiewel, Mario Döbler, Yang Yang, Bin Yang

In this work, we focus on UDA and additionally address the case of adapting not only to a single domain, but to a sequence of target domains.

Data Augmentation Semantic Segmentation +2

A Deep-Learning-Aided Pipeline for Efficient Post-Silicon Tuning

no code implementations1 Jul 2022 Yiwen Liao, Bin Yang, Raphaël Latty, Jochen Rivoir

In this sense, an more efficient tuning requires identifying the most critical tuning knobs and process parameters in terms of a given figure-of-merit for a Device Under Test (DUT).

Conditional Variable Selection for Intelligent Test

no code implementations1 Jul 2022 Yiwen Liao, Tianjie Ge, Raphaël Latty, Bin Yang

Intelligent test requires efficient and effective analysis of high-dimensional data in a large scale.

Variable Selection

RetroGraph: Retrosynthetic Planning with Graph Search

1 code implementation23 Jun 2022 Shufang Xie, Rui Yan, Peng Han, Yingce Xia, Lijun Wu, Chenjuan Guo, Bin Yang, Tao Qin

We observe that the same intermediate molecules are visited many times in the searching process, and they are usually independently treated in previous tree-based methods (e. g., AND-OR tree search, Monte Carlo tree search).

Drug Discovery Graph Neural Network +1

Federated Latent Class Regression for Hierarchical Data

no code implementations22 Jun 2022 Bin Yang, Thomas Carette, Masanobu Jimbo, Shinya Maruyama

Federated Learning (FL) allows a number of agents to participate in training a global machine learning model without disclosing locally stored data.

Federated Learning regression

Conditional Seq2Seq model for the time-dependent two-level system

no code implementations6 Jun 2022 Bin Yang, Mengxi Wu, Winfried Teizer

We apply the deep learning neural network architecture to the two-level system in quantum optics to solve the time-dependent Schrodinger equation.

Vocal Bursts Valence Prediction

$(O,G)$-granular variable precision fuzzy rough sets based on overlap and grouping functions

no code implementations18 May 2022 Wei Li, Bin Yang, Junsheng Qiao

In this paper, the depiction of $(O, G)$-granular variable precision fuzzy rough sets ($(O, G)$-GVPFRSs for short) is first given based on overlap and grouping functions.

Some neighborhood-related fuzzy covering-based rough set models and their applications for decision making

no code implementations13 May 2022 Gongao Qi, Bin Yang, Wei Li

In order to further generalize the FRS theory to more complicated data environments, we firstly propose four types of fuzzy neighborhood operators based on fuzzy covering by overlap functions and their implicators in this paper.

Decision Making

On three types of $L$-fuzzy $β$-covering-based rough sets

no code implementations13 May 2022 Wei Li, Bin Yang, Junsheng Qiao

In this paper, we mainly construct three types of $L$-fuzzy $\beta$-covering-based rough set models and study the axiom sets, matrix representations and interdependency of these three pairs of $L$-fuzzy $\beta$-covering-based rough approximation operators.


Few-Shot Object Detection in Unseen Domains

no code implementations11 Apr 2022 Karim Guirguis, George Eskandar, Matthias Kayser, Bin Yang, Juergen Beyerer

First, we leverage a meta-training paradigm, where we learn the domain shift on the base classes, then transfer the domain knowledge to the novel classes.

Domain Generalization Few-Shot Object Detection +2

Robust and Explainable Autoencoders for Unsupervised Time Series Outlier Detection---Extended Version

no code implementations7 Apr 2022 Tung Kieu, Bin Yang, Chenjuan Guo, Christian S. Jensen, Yan Zhao, Feiteng Huang, Kai Zheng

This is an extended version of "Robust and Explainable Autoencoders for Unsupervised Time Series Outlier Detection", to appear in IEEE ICDE 2022.

Outlier Detection Time Series +1

Weakly-supervised Temporal Path Representation Learning with Contrastive Curriculum Learning -- Extended Version

1 code implementation30 Mar 2022 Sean Bin Yang, Chenjuan Guo, Jilin Hu, Bin Yang, Jian Tang, Christian S. Jensen

In this setting, it is essential to learn generic temporal path representations(TPRs) that consider spatial and temporal correlations simultaneously and that can be used in different applications, i. e., downstream tasks.

Contrastive Learning Representation Learning +1

Towards Spatio-Temporal Aware Traffic Time Series Forecasting--Full Version

1 code implementation29 Mar 2022 Razvan-Gabriel Cirstea, Bin Yang, Chenjuan Guo, Tung Kieu, Shirui Pan

Such spatio-temporal agnostic models employ a shared parameter space irrespective of the time series locations and the time periods and they assume that the temporal patterns are similar across locations and do not evolve across time, which may not always hold, thus leading to sub-optimal results.

Time Series Time Series Forecasting

CMGAN: Conformer-based Metric GAN for Speech Enhancement

1 code implementation28 Mar 2022 Ruizhe Cao, Sherif Abdulatif, Bin Yang

The estimation of magnitude and complex spectrogram is decoupled in the decoder stage and then jointly incorporated to reconstruct the enhanced speech.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +4

Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs

1 code implementation17 Feb 2022 Ming Jin, Yu Zheng, Yuan-Fang Li, Siheng Chen, Bin Yang, Shirui Pan

Multivariate time series forecasting has long received significant attention in real-world applications, such as energy consumption and traffic prediction.

Multivariate Time Series Forecasting Time Series +1

Fast solver for J2-perturbed Lambert problem using deep neural network

no code implementations9 Jan 2022 Bin Yang, Shuang Li, Jinglang Feng, Massimiliano Vasile

The intelligent initial guess generator is a deep neural network that is trained to correct the initial velocity vector coming from the solution of the unperturbed Lambert problem.

AutoCTS: Automated Correlated Time Series Forecasting -- Extended Version

no code implementations21 Dec 2021 Xinle Wu, Dalin Zhang, Chenjuan Guo, Chaoyang He, Bin Yang, Christian S. Jensen

Specifically, we design both a micro and a macro search space to model possible architectures of ST-blocks and the connections among heterogeneous ST-blocks, and we provide a search strategy that is able to jointly explore the search spaces to identify optimal forecasting models.

Correlated Time Series Forecasting Time Series

BaLeNAS: Differentiable Architecture Search via the Bayesian Learning Rule

no code implementations CVPR 2022 Miao Zhang, Jilin Hu, Steven Su, Shirui Pan, Xiaojun Chang, Bin Yang, Gholamreza Haffari

Differentiable Architecture Search (DARTS) has received massive attention in recent years, mainly because it significantly reduces the computational cost through weight sharing and continuous relaxation.

Neural Architecture Search Variational Inference

Unsupervised Time Series Outlier Detection with Diversity-Driven Convolutional Ensembles -- Extended Version

no code implementations22 Nov 2021 David Campos, Tung Kieu, Chenjuan Guo, Feiteng Huang, Kai Zheng, Bin Yang, Christian S. Jensen

To improve accuracy, the ensemble employs multiple basic outlier detection models built on convolutional sequence-to-sequence autoencoders that can capture temporal dependencies in time series.

Diversity Outlier Detection +2

Spatiotemporal Representation Learning on Time Series with Dynamic Graph ODEs

no code implementations29 Sep 2021 Ming Jin, Yuan-Fang Li, Yu Zheng, Bin Yang, Shirui Pan

Spatiotemporal representation learning on multivariate time series has received tremendous attention in forecasting traffic and energy data.

Graph structure learning Representation Learning +2

USIS: Unsupervised Semantic Image Synthesis

1 code implementation29 Sep 2021 George Eskandar, Mohamed Abdelsamad, Karim Armanious, Bin Yang

Semantic Image Synthesis (SIS) is a subclass of image-to-image translation where a photorealistic image is synthesized from a segmentation mask.

Image-to-Image Translation Translation

Improving Uncertainty of Deep Learning-based Object Classification on Radar Spectra using Label Smoothing

no code implementations27 Sep 2021 Kanil Patel, William Beluch, Kilian Rambach, Michael Pfeiffer, Bin Yang

The focus of this article is to learn deep radar spectra classifiers which offer robust real-time uncertainty estimates using label smoothing during training.

Decision Making

Investigation of Uncertainty of Deep Learning-based Object Classification on Radar Spectra

no code implementations1 Jun 2021 Kanil Patel, William Beluch, Kilian Rambach, Adriana-Eliza Cozma, Michael Pfeiffer, Bin Yang

Deep learning (DL) has recently attracted increasing interest to improve object type classification for automotive radar. In addition to high accuracy, it is crucial for decision making in autonomous vehicles to evaluate the reliability of the predictions; however, decisions of DL networks are non-transparent.

Autonomous Vehicles Decision Making +3

Contrastive Learning and Self-Training for Unsupervised Domain Adaptation in Semantic Segmentation

no code implementations5 May 2021 Robert A. Marsden, Alexander Bartler, Mario Döbler, Bin Yang

To avoid the costly annotation of training data for unseen domains, unsupervised domain adaptation (UDA) attempts to provide efficient knowledge transfer from a labeled source domain to an unlabeled target domain.

Contrastive Learning Semantic Segmentation +3

Intelligent Decision Method for Main Control Parameters of Tunnel Boring Machine based on Multi-Objective Optimization of Excavation Efficiency and Cost

no code implementations29 Apr 2021 Bin Liu, Yaxu Wang, Guangzu Zhao, Bin Yang, Ruirui Wang, Dexiang Huang, Bin Xiang

Therefore, this paper proposes an intelligent decision method for the main control parameters of the TBM based on the multi-objective optimization of excavation efficiency and cost.

Graph Attention Recurrent Neural Networks for Correlated Time Series Forecasting -- Full version

no code implementations19 Mar 2021 Razvan-Gabriel Cirstea, Chenjuan Guo, Bin Yang

For example, speed sensors are deployed in different locations in a road network, where the speed of a specific location across time is captured by the corresponding sensor as a time series, resulting in multiple speed time series from different locations, which are often correlated.

Correlated Time Series Forecasting Graph Attention +1

Uncertainty-Based Biological Age Estimation of Brain MRI Scans

no code implementations15 Mar 2021 Karim Armanious, Sherif Abdulatif, Wenbin Shi, Tobias Hepp, Sergios Gatidis, Bin Yang

We apply the proposed methodology on a brain MRI dataset containing healthy individuals as well as Alzheimer's patients.

Age Estimation

Anomaly Detection Based on Selection and Weighting in Latent Space

no code implementations8 Mar 2021 Yiwen Liao, Alexander Bartler, Bin Yang

Experiments on both benchmark and real-world datasets have shown the effectiveness and superiority of SWAD.

Anomaly Detection

Modelling brain based on canonical ensemble with functional MRI: A thermodynamic exploration on neural system

no code implementations26 Feb 2021 Chenxi Zhou, Bin Yang, Wenliang Fan, Wei Li

(3) The detection of neural disease was demonstrated to be benefit from thermodynamic model, implying the immense potential of thermodynamics in auxiliary diagnosis.

SLPC: a VRNN-based approach for stochastic lidar prediction and completion in autonomous driving

no code implementations19 Feb 2021 George Eskandar, Alexander Braun, Martin Meinke, Karim Armanious, Bin Yang

Our algorithm is able to address the limitations of previous video prediction frameworks when dealing with sparse data by spatially inpainting the depth maps in the upcoming frames.

Autonomous Driving Decision Making +2

Condensed Composite Memory Continual Learning

1 code implementation19 Feb 2021 Felix Wiewel, Bin Yang

While many recently proposed methods for continual learning use some training examples for rehearsal, their performance strongly depends on the number of stored examples.

Continual Learning

Auto4D: Learning to Label 4D Objects from Sequential Point Clouds

no code implementations17 Jan 2021 Bin Yang, Min Bai, Ming Liang, Wenyuan Zeng, Raquel Urtasun

The key idea is to decompose the 4D object label into two parts: the object size in 3D that's fixed through time for rigid objects, and the motion path describing the evolution of the object's pose through time.

3D Object Detection Object

PLUMENet: Efficient 3D Object Detection from Stereo Images

1 code implementation17 Jan 2021 Yan Wang, Bin Yang, Rui Hu, Ming Liang, Raquel Urtasun

In this paper we propose a model that unifies these two tasks and performs them in the same metric space.

3D Object Detection From Stereo Images Depth Estimation +2

End-to-end Interpretable Neural Motion Planner

1 code implementation CVPR 2019 Wenyuan Zeng, Wenjie Luo, Simon Suo, Abbas Sadat, Bin Yang, Sergio Casas, Raquel Urtasun

In this paper, we propose a neural motion planner (NMP) for learning to drive autonomously in complex urban scenarios that include traffic-light handling, yielding, and interactions with multiple road-users.

Diverse Complexity Measures for Dataset Curation in Self-driving

no code implementations16 Jan 2021 Abbas Sadat, Sean Segal, Sergio Casas, James Tu, Bin Yang, Raquel Urtasun, Ersin Yumer

Our experiments on a wide range of tasks and models show that the proposed curation pipeline is able to select datasets that lead to better generalization and higher performance.

Active Learning Motion Forecasting +1

Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net

no code implementations CVPR 2018 Wenjie Luo, Bin Yang, Raquel Urtasun

In this paper we propose a novel deep neural network that is able to jointly reason about 3D detection, tracking and motion forecasting given data captured by a 3D sensor.

Motion Forecasting

HDNET: Exploiting HD Maps for 3D Object Detection

no code implementations21 Dec 2020 Bin Yang, Ming Liang, Raquel Urtasun

In this paper we show that High-Definition (HD) maps provide strong priors that can boost the performance and robustness of modern 3D object detectors.

3D Object Detection Object +1

Deep Continuous Fusion for Multi-Sensor 3D Object Detection

no code implementations ECCV 2018 Ming Liang, Bin Yang, Shenlong Wang, Raquel Urtasun

In this paper, we propose a novel 3D object detector that can exploit both LIDAR as well as cameras to perform very accurate localization.

3D Object Detection Object +1

Recovering and Simulating Pedestrians in the Wild

no code implementations16 Nov 2020 Ze Yang, Siva Manivasagam, Ming Liang, Bin Yang, Wei-Chiu Ma, Raquel Urtasun

We then incorporate the reconstructed pedestrian assets bank in a realistic LiDAR simulation system by performing motion retargeting, and show that the simulated LiDAR data can be used to significantly reduce the amount of annotated real-world data required for visual perception tasks.

Data Augmentation motion retargeting

Perceive, Attend, and Drive: Learning Spatial Attention for Safe Self-Driving

no code implementations2 Nov 2020 Bob Wei, Mengye Ren, Wenyuan Zeng, Ming Liang, Bin Yang, Raquel Urtasun

In this paper, we propose an end-to-end self-driving network featuring a sparse attention module that learns to automatically attend to important regions of the input.

Motion Planning

Feature Selection Using Batch-Wise Attenuation and Feature Mask Normalization

no code implementations26 Oct 2020 Yiwen Liao, Raphaël Latty, Bin Yang

Feature selection is generally used as one of the most important preprocessing techniques in machine learning, as it helps to reduce the dimensionality of data and assists researchers and practitioners in understanding data.

feature selection

Investigating Cross-Domain Losses for Speech Enhancement

no code implementations20 Oct 2020 Sherif Abdulatif, Karim Armanious, Jayasankar T. Sajeev, Karim Guirguis, Bin Yang

Recent years have seen a surge in the number of available frameworks for speech enhancement (SE) and recognition.

Speech Enhancement

V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Prediction

3 code implementations ECCV 2020 Tsun-Hsuan Wang, Sivabalan Manivasagam, Ming Liang, Bin Yang, Wenyuan Zeng, James Tu, Raquel Urtasun

In this paper, we explore the use of vehicle-to-vehicle (V2V) communication to improve the perception and motion forecasting performance of self-driving vehicles.

3D Object Detection Motion Forecasting

DSDNet: Deep Structured self-Driving Network

no code implementations ECCV 2020 Wenyuan Zeng, Shenlong Wang, Renjie Liao, Yun Chen, Bin Yang, Raquel Urtasun

In this paper, we propose the Deep Structured self-Driving Network (DSDNet), which performs object detection, motion prediction, and motion planning with a single neural network.

Motion Planning motion prediction +2

Force myography benchmark data for hand gesture recognition and transfer learning

1 code implementation29 Jul 2020 Thomas Buhl Andersen, Rógvi Eliasen, Mikkel Jarlund, Bin Yang

We contribute to the advancement of this field by making accessible a benchmark dataset collected using a commercially available sensor setup from 20 persons covering 18 unique gestures, in the hope of allowing further comparison of results as well as easier entry into this field of research.

Hand Gesture Recognition Hand-Gesture Recognition +1

RadarNet: Exploiting Radar for Robust Perception of Dynamic Objects

no code implementations ECCV 2020 Bin Yang, Runsheng Guo, Ming Liang, Sergio Casas, Raquel Urtasun

We tackle the problem of exploiting Radar for perception in the context of self-driving as Radar provides complementary information to other sensors such as LiDAR or cameras in the form of Doppler velocity.

object-detection Object Detection

Learning Lane Graph Representations for Motion Forecasting

1 code implementation ECCV 2020 Ming Liang, Bin Yang, Rui Hu, Yun Chen, Renjie Liao, Song Feng, Raquel Urtasun

We propose a motion forecasting model that exploits a novel structured map representation as well as actor-map interactions.

Motion Forecasting Trajectory Prediction

Multi-Class Uncertainty Calibration via Mutual Information Maximization-based Binning

1 code implementation ICLR 2021 Kanil Patel, William Beluch, Bin Yang, Michael Pfeiffer, Dan Zhang

The goal of this paper is to resolve the identified issues of HB in order to provide calibrated confidence estimates using only a small holdout calibration dataset for bin optimization while preserving multi-class ranking accuracy.


LiDARsim: Realistic LiDAR Simulation by Leveraging the Real World

no code implementations CVPR 2020 Sivabalan Manivasagam, Shenlong Wang, Kelvin Wong, Wenyuan Zeng, Mikita Sazanovich, Shuhan Tan, Bin Yang, Wei-Chiu Ma, Raquel Urtasun

We first utilize ray casting over the 3D scene and then use a deep neural network to produce deviations from the physics-based simulation, producing realistic LiDAR point clouds.

Physically Realizable Adversarial Examples for LiDAR Object Detection

no code implementations CVPR 2020 James Tu, Mengye Ren, Siva Manivasagam, Ming Liang, Bin Yang, Richard Du, Frank Cheng, Raquel Urtasun

Modern autonomous driving systems rely heavily on deep learning models to process point cloud sensory data; meanwhile, deep models have been shown to be susceptible to adversarial attacks with visually imperceptible perturbations.

Adversarial Defense Autonomous Driving +4

Infinitely Wide Graph Convolutional Networks: Semi-supervised Learning via Gaussian Processes

no code implementations26 Feb 2020 Jilin Hu, Jianbing Shen, Bin Yang, Ling Shao

Graph convolutional neural networks~(GCNs) have recently demonstrated promising results on graph-based semi-supervised classification, but little work has been done to explore their theoretical properties.

Gaussian Processes General Classification

On-manifold Adversarial Data Augmentation Improves Uncertainty Calibration

no code implementations16 Dec 2019 Kanil Patel, William Beluch, Dan Zhang, Michael Pfeiffer, Bin Yang

Uncertainty estimates help to identify ambiguous, novel, or anomalous inputs, but the reliable quantification of uncertainty has proven to be challenging for modern deep networks.

Adversarial Attack Data Augmentation

ipA-MedGAN: Inpainting of Arbitrary Regions in Medical Imaging

no code implementations21 Oct 2019 Karim Armanious, Vijeth Kumar, Sherif Abdulatif, Tobias Hepp, Sergios Gatidis, Bin Yang

Local deformations in medical modalities are common phenomena due to a multitude of factors such as metallic implants or limited field of views in magnetic resonance imaging (MRI).

Image Inpainting

AeGAN: Time-Frequency Speech Denoising via Generative Adversarial Networks

no code implementations21 Oct 2019 Sherif Abdulatif, Karim Armanious, Karim Guirguis, Jayasankar T. Sajeev, Bin Yang

Automatic speech recognition (ASR) systems are of vital importance nowadays in commonplace tasks such as speech-to-text processing and language translation.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +6

Organ-based Chronological Age Estimation based on 3D MRI Scans

no code implementations14 Oct 2019 Karim Armanious, Sherif Abdulatif, Anish Rao Bhaktharaguttu, Thomas Küstner, Tobias Hepp, Sergios Gatidis, Bin Yang

Individuals age differently depending on a multitude of different factors such as lifestyle, medical history and genetics.

Age Estimation

Enhancing Flood Impact Analysis using Interactive Retrieval of Social Media Images

1 code implementation9 Aug 2019 Björn Barz, Kai Schröter, Moritz Münch, Bin Yang, Andrea Unger, Doris Dransch, Joachim Denzler

The analysis of natural disasters such as floods in a timely manner often suffers from limited data due to a coarse distribution of sensors or sensor failures.

Content-Based Image Retrieval Retrieval

PathRank: A Multi-Task Learning Framework to Rank Paths in Spatial Networks

no code implementations9 Jul 2019 Sean Bin Yang, Bin Yang

The objective function is designed to consider errors on both ranking scores and spatial properties, making the framework a multi-task learning framework.

Multi-Task Learning Network Embedding +1

Localizing Catastrophic Forgetting in Neural Networks

no code implementations6 Jun 2019 Felix Wiewel, Bin Yang

Artificial neural networks (ANNs) suffer from catastrophic forgetting when trained on a sequence of tasks.

Continual Learning

Unsupervised Medical Image Translation Using Cycle-MedGAN

no code implementations8 Mar 2019 Karim Armanious, Chenming Jiang, Sherif Abdulatif, Thomas Küstner, Sergios Gatidis, Bin Yang

The proposed framework utilizes new non-adversarial cycle losses which direct the framework to minimize the textural and perceptual discrepancies in the translated images.

Image-to-Image Translation Translation

An Adversarial Super-Resolution Remedy for Radar Design Trade-offs

no code implementations4 Mar 2019 Karim Armanious, Sherif Abdulatif, Fady Aziz, Urs Schneider, Bin Yang

Radar is of vital importance in many fields, such as autonomous driving, safety and surveillance applications.

Autonomous Driving Super-Resolution

Active Learning for One-Class Classification Using Two One-Class Classifiers

no code implementations10 Jan 2019 Patrick Schlachter, Bin Yang

Active learning methods play an important role to reduce the efforts of manual labeling in the field of machine learning.

Active Learning General Classification +2

One-Class Feature Learning Using Intra-Class Splitting

no code implementations20 Dec 2018 Patrick Schlachter, Yiwen Liao, Bin Yang

This paper proposes a novel generic one-class feature learning method based on intra-class splitting.

Classification General Classification +2

Non-invasive measuring method of skin temperature based on skin sensitivity index and deep learning

no code implementations16 Dec 2018 Xiaogang Cheng, Bin Yang, Kaige Tan, Erik Isaksson, Liren Li, Anders Hedman, Thomas Olofsson, Hai-Bo Li

Due to the challenges of intra- and inter-individual differences and skin subtleness variations, there is no satisfactory solution for thermal comfort measurements until now.

Person Identification and Body Mass Index: A Deep Learning-Based Study on Micro-Dopplers

no code implementations17 Nov 2018 Sherif Abdulatif, Fady Aziz, Karim Armanious, Bernhard Kleiner, Bin Yang, Urs Schneider

In our proposed experimental setup, a treadmill is used to collect $\boldsymbol{\mu}$-D signatures of 22 subjects with different genders and body characteristics.

Person Identification

Recurrent Multi-Graph Neural Networks for Travel Cost Prediction

no code implementations13 Nov 2018 Jilin Hu, Chenjuan Guo, Bin Yang, Christian S. Jensen, Lu Chen

Origin-destination (OD) matrices are often used in urban planning, where a city is partitioned into regions and an element (i, j) in an OD matrix records the cost (e. g., travel time, fuel consumption, or travel speed) from region i to region j.

Towards Adversarial Denoising of Radar Micro-Doppler Signatures

no code implementations12 Nov 2018 Sherif Abdulatif, Karim Armanious, Fady Aziz, Urs Schneider, Bin Yang

Two sets of experiments were collected on 22 subjects walking on a treadmill at an intermediate velocity using a \unit[25]{GHz} CW radar.

Denoising Denoising Of Radar Micro-Doppler Signatures +1

Deep Neural Network inference with reduced word length

no code implementations23 Oct 2018 Lukas Mauch, Bin Yang

Deep neural networks (DNN) are powerful models for many pattern recognition tasks, yet their high computational complexity and memory requirement limit them to applications on high-performance computing platforms.

Retrospective correction of Rigid and Non-Rigid MR motion artifacts using GANs

no code implementations17 Sep 2018 Karim Armanious, Sergios Gatidis, Konstantin Nikolaou, Bin Yang, Thomas Küstner

Motion artifacts are a primary source of magnetic resonance (MR) image quality deterioration with strong repercussions on diagnostic performance.

Correlated Time Series Forecasting using Deep Neural Networks: A Summary of Results

no code implementations29 Aug 2018 Razvan-Gabriel Cirstea, Darius-Valer Micu, Gabriel-Marcel Muresan, Chenjuan Guo, Bin Yang

To enable accurate forecasting on such correlated time series, this paper proposes two models that combine convolutional neural networks (CNNs) and recurrent neural networks (RNNs).

Correlated Time Series Forecasting Multi-Task Learning +1

MedGAN: Medical Image Translation using GANs

no code implementations17 Jun 2018 Karim Armanious, Chenming Jiang, Marc Fischer, Thomas Küstner, Konstantin Nikolaou, Sergios Gatidis, Bin Yang

Image-to-image translation is considered a new frontier in the field of medical image analysis, with numerous potential applications.

Decoder Image Denoising +3

Learning to Reweight Examples for Robust Deep Learning

9 code implementations ICML 2018 Mengye Ren, Wenyuan Zeng, Bin Yang, Raquel Urtasun

Deep neural networks have been shown to be very powerful modeling tools for many supervised learning tasks involving complex input patterns.


Multi-level Attention Model for Weakly Supervised Audio Classification

5 code implementations6 Mar 2018 Changsong Yu, Karim Said Barsim, Qiuqiang Kong, Bin Yang

The objective of audio classification is to predict the presence or absence of audio events in an audio clip.

Audio Classification

Learning to Route with Sparse Trajectory Sets---Extended Version

no code implementations22 Feb 2018 Chenjuan Guo, Bin Yang, Jilin Hu, Christian S. Jensen

In the second step, we exploit the above graph-like structure to achieve a comprehensive trajectory-based routing solution.


Neural Network Ensembles to Real-time Identification of Plug-level Appliance Measurements

no code implementations20 Feb 2018 Karim Said Barsim, Lukas Mauch, Bin Yang

The problem of identifying end-use electrical appliances from their individual consumption profiles, known as the appliance identification problem, is a primary stage in both Non-Intrusive Load Monitoring (NILM) and automated plug-wise metering.

Non-Intrusive Load Monitoring

On the Feasibility of Generic Deep Disaggregation for Single-Load Extraction

no code implementations5 Feb 2018 Karim Said Barsim, Bin Yang

Recently, and with the growing development of big energy datasets, data-driven learning techniques began to represent a potential solution to the energy disaggregation problem outperforming engineered and hand-crafted models.

Selective Sampling and Mixture Models in Generative Adversarial Networks

no code implementations2 Feb 2018 Karim Said Barsim, Lirong Yang, Bin Yang

In this paper, we propose a multi-generator extension to the adversarial training framework, in which the objective of each generator is to represent a unique component of a target mixture distribution.

SBNet: Sparse Blocks Network for Fast Inference

2 code implementations CVPR 2018 Mengye Ren, Andrei Pokrovsky, Bin Yang, Raquel Urtasun

Conventional deep convolutional neural networks (CNNs) apply convolution operators uniformly in space across all feature maps for hundreds of layers - this incurs a high computational cost for real-time applications.

3D Object Detection Object +2

TorontoCity: Seeing the World with a Million Eyes

no code implementations ICCV 2017 Shenlong Wang, Min Bai, Gellert Mattyus, Hang Chu, Wenjie Luo, Bin Yang, Justin Liang, Joel Cheverie, Sanja Fidler, Raquel Urtasun

In this paper we introduce the TorontoCity benchmark, which covers the full greater Toronto area (GTA) with 712. 5 $km^2$ of land, 8439 $km$ of road and around 400, 000 buildings.

Instance Segmentation Semantic Segmentation

Crafting GBD-Net for Object Detection

1 code implementation8 Oct 2016 Xingyu Zeng, Wanli Ouyang, Junjie Yan, Hongsheng Li, Tong Xiao, Kun Wang, Yu Liu, Yucong Zhou, Bin Yang, Zhe Wang, Hui Zhou, Xiaogang Wang

The effectiveness of GBD-Net is shown through experiments on three object detection datasets, ImageNet, Pascal VOC2007 and Microsoft COCO.

Object object-detection +1

CRAFT Objects from Images

1 code implementation CVPR 2016 Bin Yang, Junjie Yan, Zhen Lei, Stan Z. Li

They decompose the object detection problem into two cascaded easier tasks: 1) generating object proposals from images, 2) classifying proposals into various object categories.

Object object-detection +2