Search Results for author: Kai Huang

Found 41 papers, 12 papers with code

Financial Default Prediction via Motif-preserving Graph Neural Network with Curriculum Learning

no code implementations11 Mar 2024 Daixin Wang, Zhiqiang Zhang, Yeyu Zhao, Kai Huang, Yulin kang, Jun Zhou

In this paper, we fill in this gap by proposing a motif-preserving Graph Neural Network with curriculum learning (MotifGNN) to jointly learn the lower-order structures from the original graph and higherorder structures from multi-view motif-based graphs for financial default prediction.

Binary Classification

NIV-SSD: Neighbor IoU-Voting Single-Stage Object Detector From Point Cloud

1 code implementation23 Jan 2024 Shuai Liu, Di Wang, Quan Wang, Kai Huang

NIV strategy can serve as a bridge between classification and regression branches by calculating two types of statistical data from the regression output to correct the classification confidence.

Classification Data Augmentation +1

DCDet: Dynamic Cross-based 3D Object Detector

1 code implementation14 Jan 2024 Shuai Liu, Boyang Li, Zhiyu Fang, Kai Huang

We find that the center-based label assignment often fails to generate sufficient positive samples for training, while the anchor-based label assignment tends to encounter an imbalanced issue when handling objects of varying scales.

3D Object Detection Object +2

ElasticTrainer: Speeding Up On-Device Training with Runtime Elastic Tensor Selection

1 code implementation21 Dec 2023 Kai Huang, Boyuan Yang, Wei Gao

To speed up on-device training, existing schemes select trainable NN portion offline or conduct unrecoverable selection at runtime, but the evolution of trainable NN portion is constrained and cannot adapt to the current need for training.

Real-time Neural Network Inference on Extremely Weak Devices: Agile Offloading with Explainable AI

no code implementations21 Dec 2023 Kai Huang, Wei Gao

With the wide adoption of AI applications, there is a pressing need of enabling real-time neural network (NN) inference on small embedded devices, but deploying NNs and achieving high performance of NN inference on these small devices is challenging due to their extremely weak capabilities.

Modality Plug-and-Play: Elastic Modality Adaptation in Multimodal LLMs for Embodied AI

1 code implementation13 Dec 2023 Kai Huang, Boyuan Yang, Wei Gao

Large Language Models (LLMs) are capable of reasoning over diverse input data modalities through pre-trained encoders.

Holistic Inverse Rendering of Complex Facade via Aerial 3D Scanning

no code implementations20 Nov 2023 Zixuan Xie, Rengan Xie, Rong Li, Kai Huang, Pengju Qiao, Jingsen Zhu, Xu Yin, Qi Ye, Wei Hua, Yuchi Huo, Hujun Bao

In this work, we use multi-view aerial images to reconstruct the geometry, lighting, and material of facades using neural signed distance fields (SDFs).

Benchmarking Inverse Rendering +2

EyeLS: Shadow-Guided Instrument Landing System for Intraocular Target Approaching in Robotic Eye Surgery

no code implementations15 Nov 2023 Junjie Yang, Zhihao Zhao, Siyuan Shen, Daniel Zapp, Mathias Maier, Kai Huang, Nassir Navab, M. Ali Nasseri

Robotic ophthalmic surgery is an emerging technology to facilitate high-precision interventions such as retina penetration in subretinal injection and removal of floating tissues in retinal detachment depending on the input imaging modalities such as microscopy and intraoperative OCT (iOCT).

Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation

1 code implementation22 Sep 2023 Kai Huang, Hanyun Yin, Heng Huang, Wei Gao

With the fast growth of LLM-enabled AI applications and democratization of open-souced LLMs, fine-tuning has become possible for non-expert individuals, but intensively performed LLM fine-tuning worldwide could result in significantly high energy consumption and carbon footprint, which may bring large environmental impact.

Abstractive Text Summarization

Prototypical Kernel Learning and Open-set Foreground Perception for Generalized Few-shot Semantic Segmentation

no code implementations ICCV 2023 Kai Huang, Feigege Wang, Ye Xi, Yutao Gao

Then, we explore to merge the prototypical learning to the update of base-class kernels, which is consistent with the prototype knowledge aggregation of few-shot novel classes.

Generalized Few-Shot Semantic Segmentation Segmentation +1

Language-Conditioned Imitation Learning with Base Skill Priors under Unstructured Data

no code implementations30 May 2023 Hongkuan Zhou, Zhenshan Bing, Xiangtong Yao, Xiaojie Su, Chenguang Yang, Kai Huang, Alois Knoll

In this evaluation, we set up ten tasks and achieved an average 30% improvement in our approach compared to the current state-of-the-art approach, demonstrating a high generalization capability in both simulated environments and the real world.

Imitation Learning Robot Manipulation

DIVA: A Dirichlet Process Mixtures Based Incremental Deep Clustering Algorithm via Variational Auto-Encoder

1 code implementation23 May 2023 Zhenshan Bing, Yuan Meng, Yuqi Yun, Hang Su, Xiaojie Su, Kai Huang, Alois Knoll

Generative model-based deep clustering frameworks excel in classifying complex data, but are limited in handling dynamic and complex features because they require prior knowledge of the number of clusters.

Clustering Image Generation +2

Meta-Reinforcement Learning Based on Self-Supervised Task Representation Learning

no code implementations29 Apr 2023 Mingyang Wang, Zhenshan Bing, Xiangtong Yao, Shuai Wang, Hang Su, Chenguang Yang, Kai Huang, Alois Knoll

On MuJoCo and Meta-World benchmarks, MoSS outperforms prior works in terms of asymptotic performance, sample efficiency (3-50x faster), adaptation efficiency, and generalization robustness on broad and diverse task distributions.

Meta Reinforcement Learning reinforcement-learning +1

Efficient Halftoning via Deep Reinforcement Learning

no code implementations24 Apr 2023 Haitian Jiang, Dongliang Xiong, Xiaowen Jiang, Li Ding, Liang Chen, Kai Huang

In this paper, we propose a fast and structure-aware halftoning method via a data-driven approach.

reinforcement-learning SSIM

Towards Spatio-temporal Sea Surface Temperature Forecasting via Static and Dynamic Learnable Personalized Graph Convolution Network

no code implementations12 Apr 2023 Xiaohan Li, Gaowei Zhang, Kai Huang, Zhaofeng He

Sea surface temperature (SST) is uniquely important to the Earth's atmosphere since its dynamics are a major force in shaping local and global climate and profoundly affect our ecosystems.

Graph Learning

Towards human-compatible autonomous car: A study of non-verbal Turing test in automated driving with affective transition modelling

1 code implementation6 Dec 2022 Zhaoning Li, Qiaoli Jiang, Zhengming Wu, Anqi Liu, Haiyan Wu, Miner Huang, Kai Huang, Yixuan Ku

The present study tested whether the AI driver could create a human-like ride experience for passengers based on 69 participants' feedback in a real-road scenario.

Autonomous Driving

A Joint Framework Towards Class-aware and Class-agnostic Alignment for Few-shot Segmentation

no code implementations2 Nov 2022 Kai Huang, Mingfei Cheng, Yang Wang, Bochen Wang, Ye Xi, Feigege Wang, Peng Chen

Few-shot segmentation (FSS) aims to segment objects of unseen classes given only a few annotated support images.

Segmentation

Halftoning with Multi-Agent Deep Reinforcement Learning

no code implementations23 Jul 2022 Haitian Jiang, Dongliang Xiong, Xiaowen Jiang, Aiguo Yin, Li Ding, Kai Huang

Deep neural networks have recently succeeded in digital halftoning using vanilla convolutional layers with high parallelism.

reinforcement-learning Reinforcement Learning (RL)

A Learned Index for Exact Similarity Search in Metric Spaces

no code implementations21 Apr 2022 Yao Tian, Tingyun Yan, Xi Zhao, Kai Huang, Xiaofang Zhou

In this paper, we propose a novel indexing approach called LIMS that uses data clustering, pivot-based data transformation techniques and learned indexes to support efficient similarity query processing in metric spaces.

BIG-bench Machine Learning

BigDL 2.0: Seamless Scaling of AI Pipelines from Laptops to Distributed Cluster

1 code implementation CVPR 2022 Jason Dai, Ding Ding, Dongjie Shi, Shengsheng Huang, Jiao Wang, Xin Qiu, Kai Huang, Guoqiong Song, Yang Wang, Qiyuan Gong, Jiaming Song, Shan Yu, Le Zheng, Yina Chen, Junwei Deng, Ge Song

To address this challenge, we have open sourced BigDL 2. 0 at https://github. com/intel-analytics/BigDL/ under Apache 2. 0 license (combining the original BigDL and Analytics Zoo projects); using BigDL 2. 0, users can simply build conventional Python notebooks on their laptops (with possible AutoML support), which can then be transparently accelerated on a single node (with up-to 9. 6x speedup in our experiments), and seamlessly scaled out to a large cluster (across several hundreds servers in real-world use cases).

AutoML Distributed Computing +1

Monolithic Integrated Multiband Acoustic Devices on Heterogeneous Substrate for Sub-6 GHz RF-FEMs

no code implementations20 Oct 2021 Shibin Zhang, Hongyan Zhou, Pengcheng Zheng, Jinbo Wu, Liping Zhang, Zhongxu Li, Kai Huang, Xin Ou, Xi Wang

Monolithic integration of multiband (1. 4~ 6. 0 GHz) RF acoustic devices were successfully demonstrated within the same process flow by using the lithium niobate (LN) thin film on silicon carbide (LNOSiC) substrate.

Towards Cognitive Navigation: Design and Implementation of a Biologically Inspired Head Direction Cell Network

no code implementations22 Sep 2021 Zhenshan Bing, Amir EI Sewisy, Genghang Zhuang, Florian Walter, Fabrice O. Morin, Kai Huang, Alois Knoll

As a vital cognitive function of animals, the navigation skill is first built on the accurate perception of the directional heading in the environment.

Meta-Reinforcement Learning in Broad and Non-Parametric Environments

1 code implementation8 Aug 2021 Zhenshan Bing, Lukas Knak, Fabrice Oliver Robin, Kai Huang, Alois Knoll

Recent state-of-the-art artificial agents lack the ability to adapt rapidly to new tasks, as they are trained exclusively for specific objectives and require massive amounts of interaction to learn new skills.

Meta Reinforcement Learning reinforcement-learning +1

Adaptive Logit Adjustment Loss for Long-Tailed Visual Recognition

no code implementations13 Apr 2021 Yan Zhao, Weicong Chen, Xu Tan, Kai Huang, Jihong Zhu

The adaptive adjusting term is composed of two complementary factors: 1) quantity factor, which pays more attention to tail classes, and 2) difficulty factor, which adaptively pays more attention to hard instances in the training process.

General Classification Semantic Similarity +1

Pseudo-Loss Confidence Metric for Semi-Supervised Few-Shot Learning

no code implementations ICCV 2021 Kai Huang, Jie Geng, Wen Jiang, Xinyang Deng, Zhe Xu

Most semi-supervised few-shot learning methods select pseudo-labeled data of unlabeled set by task-specific confidence estimation.

Few-Shot Learning

Context-Aware Drive-thru Recommendation Service at Fast Food Restaurants

no code implementations13 Oct 2020 Luyang Wang, Kai Huang, Jiao Wang, Shengsheng Huang, Jason Dai, Yue Zhuang

Drive-thru is a popular sales channel in the fast food industry where consumers can make food purchases without leaving their cars.

Recommendation Systems

3D Object Detection and Tracking Based on Streaming Data

no code implementations14 Sep 2020 Xusen Guo, Jiangfeng Gu, Silu Guo, Zixiao Xu, Chengzhang Yang, Shanghua Liu, Long Cheng, Kai Huang

Recent approaches for 3D object detection have made tremendous progresses due to the development of deep learning.

3D Object Detection Object +2

Complex Robotic Manipulation via Graph-Based Hindsight Goal Generation

1 code implementation27 Jul 2020 Zhenshan Bing, Matthias Brucker, Fabrice O. Morin, Kai Huang, Alois Knoll

In this paper, we propose graph-based hindsight goal generation (G-HGG), an extension of HGG selecting hindsight goals based on shortest distances in an obstacle-avoiding graph, which is a discrete representation of the environment.

Large-scale Uncertainty Estimation and Its Application in Revenue Forecast of SMEs

no code implementations2 May 2020 Zebang Zhang, Kui Zhao, Kai Huang, Quanhui Jia, Yanming Fang, Quan Yu

If the uncertainty of an enterprise's revenue forecasting can be estimated, a more proper credit limit can be granted.

Management Uncertainty Quantification

Indirect and Direct Training of Spiking Neural Networks for End-to-End Control of a Lane-Keeping Vehicle

no code implementations10 Mar 2020 Zhenshan Bing, Claus Meschede, Guang Chen, Alois Knoll, Kai Huang

Building spiking neural networks (SNNs) based on biological synaptic plasticities holds a promising potential for accomplishing fast and energy-efficient computing, which is beneficial to mobile robotic applications.

Q-Learning

PhoneBit: Efficient GPU-Accelerated Binary Neural Network Inference Engine for Mobile Phones

no code implementations5 Dec 2019 Gang Chen, Shengyu He, Haitao Meng, Kai Huang

Over the last years, a great success of deep neural networks (DNNs) has been witnessed in computer vision and other fields.

Bridge Video and Text with Cascade Syntactic Structure

no code implementations COLING 2018 Guolong Wang, Zheng Qin, Kaiping Xu, Kai Huang, Shuxiong Ye

We present a video captioning approach that encodes features by progressively completing syntactic structure (LSTM-CSS).

Attribute Object +3

BigDL: A Distributed Deep Learning Framework for Big Data

1 code implementation16 Apr 2018 Jason Dai, Yiheng Wang, Xin Qiu, Ding Ding, Yao Zhang, Yanzhang Wang, Xianyan Jia, Cherry Zhang, Yan Wan, Zhichao Li, Jiao Wang, Shengsheng Huang, Zhongyuan Wu, Yang Wang, Yuhao Yang, Bowen She, Dongjie Shi, Qi Lu, Kai Huang, Guoqiong Song

This paper presents BigDL (a distributed deep learning framework for Apache Spark), which has been used by a variety of users in the industry for building deep learning applications on production big data platforms.

Fraud Detection Management +1

Planecell: Representing the 3D Space with Planes

no code implementations30 Mar 2017 Lei Fan, Ziyu Pan, Long Chen, Kai Huang

Reconstruction based on the stereo camera has received considerable attention recently, but two particular challenges still remain.

Image Segmentation Semantic Segmentation

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