Search Results for author: Jonathan Li

Found 47 papers, 10 papers with code

Evaluating AI for Law: Bridging the Gap with Open-Source Solutions

no code implementations18 Apr 2024 Rohan Bhambhoria, Samuel Dahan, Jonathan Li, Xiaodan Zhu

This study evaluates the performance of general-purpose AI, like ChatGPT, in legal question-answering tasks, highlighting significant risks to legal professionals and clients.

SambaLingo: Teaching Large Language Models New Languages

no code implementations8 Apr 2024 Zoltan Csaki, Bo Li, Jonathan Li, Qiantong Xu, Pian Pawakapan, Leon Zhang, Yun Du, Hengyu Zhao, Changran Hu, Urmish Thakker

In this paper, we present a comprehensive investigation into the adaptation of LLMs to new languages.

Neighborhood Attention Makes the Encoder of ResUNet Stronger for Accurate Road Extraction

1 code implementation8 Jun 2023 Ali Jamali, Swalpa Kumar Roy, Jonathan Li, Pedram Ghamisi

In the domain of remote sensing image interpretation, road extraction from high-resolution aerial imagery has already been a hot research topic.

Segmentation Semantic Segmentation

Dynamic Clustering Transformer Network for Point Cloud Segmentation

no code implementations30 May 2023 Dening Lu, Jun Zhou, Kyle Yilin Gao, Dilong Li, Jing Du, Linlin Xu, Jonathan Li

Specifically, we propose novel semantic feature-based dynamic sampling and clustering methods in the encoder, which enables the model to be aware of local semantic homogeneity for local feature aggregation.

Clustering Point Cloud Segmentation +1

Prefix Propagation: Parameter-Efficient Tuning for Long Sequences

1 code implementation20 May 2023 Jonathan Li, Will Aitken, Rohan Bhambhoria, Xiaodan Zhu

Parameter-efficient tuning aims to mitigate the large memory requirements of adapting pretrained language models for downstream tasks.

Parameter-Efficient Legal Domain Adaptation

no code implementations25 Oct 2022 Jonathan Li, Rohan Bhambhoria, Xiaodan Zhu

Unfortunately, parameter-efficient methods perform poorly with small amounts of data, which are common in the legal domain (where data labelling costs are high).

Domain Adaptation

NeRF: Neural Radiance Field in 3D Vision, A Comprehensive Review

no code implementations1 Oct 2022 Kyle Gao, Yina Gao, Hongjie He, Dening Lu, Linlin Xu, Jonathan Li

Neural Radiance Field (NeRF) has recently become a significant development in the field of Computer Vision, allowing for implicit, neural network-based scene representation and novel view synthesis.

3D Reconstruction Autonomous Navigation +1

3DGTN: 3D Dual-Attention GLocal Transformer Network for Point Cloud Classification and Segmentation

no code implementations21 Sep 2022 Dening Lu, Kyle Gao, Qian Xie, Linlin Xu, Jonathan Li

This paper presents a novel point cloud representational learning network, called 3D Dual Self-attention Global Local (GLocal) Transformer Network (3DGTN), for improved feature learning in both classification and segmentation tasks, with the following key contributions.

Classification Point Cloud Classification +1

Transformers in 3D Point Clouds: A Survey

no code implementations16 May 2022 Dening Lu, Qian Xie, Mingqiang Wei, Kyle Gao, Linlin Xu, Jonathan Li

To demonstrate the superiority of Transformers in point cloud analysis, we present comprehensive comparisons of various Transformer-based methods for classification, segmentation, and object detection.

object-detection Object Detection +1

3DCTN: 3D Convolution-Transformer Network for Point Cloud Classification

1 code implementation2 Mar 2022 Dening Lu, Qian Xie, Linlin Xu, Jonathan Li

This paper presents a novel hierarchical framework that incorporates convolution with Transformer for point cloud classification, named 3D Convolution-Transformer Network (3DCTN), to combine the strong and efficient local feature learning ability of convolution with the remarkable global context modeling capability of Transformer.

Classification Point Cloud Classification

Box2Seg: Learning Semantics of 3D Point Clouds with Box-Level Supervision

no code implementations9 Jan 2022 Yan Liu, Qingyong Hu, Yinjie Lei, Kai Xu, Jonathan Li, Yulan Guo

In this paper, we introduce a neural architecture, termed Box2Seg, to learn point-level semantics of 3D point clouds with bounding box-level supervision.

Semantic Segmentation

Deep Reinforcement Learning for Equal Risk Option Pricing and Hedging under Dynamic Expectile Risk Measures

no code implementations29 Sep 2021 Saeed Marzban, Erick Delage, Jonathan Li

Recently equal risk pricing, a framework for fair derivative pricing, was extended to consider coherent risk measures.

WaveCorr: Deep Reinforcement Learning with Permutation Invariant Policy Networks for Portfolio Management

no code implementations29 Sep 2021 Saeed Marzban, Erick Delage, Jonathan Li

In this paper, we present a new portfolio policy network architecture for deep reinforcement learning (DRL) that can exploit more effectively cross-asset dependency information and achieve better performance than state-of-the-art architectures.

Decision Making Management +2

Direction-aware Feature-level Frequency Decomposition for Single Image Deraining

no code implementations15 Jun 2021 Sen Deng, Yidan Feng, Mingqiang Wei, Haoran Xie, Yiping Chen, Jonathan Li, Xiao-Ping Zhang, Jing Qin

Second, we further establish communication channels between low-frequency maps and high-frequency maps to interactively capture structures from high-frequency maps and add them back to low-frequency maps and, simultaneously, extract details from low-frequency maps and send them back to high-frequency maps, thereby removing rain streaks while preserving more delicate features in the input image.

Single Image Deraining

Monitoring surface deformation over oilfield using MT-InSAR and production well data

no code implementations18 Mar 2021 Sarah Narges Fatholahi, Hongjie He, Lanying Wang, Awase Syed, Jonathan Li

Surface displacements associated with the average subsidence due to hydrocarbon exploitation in southwest of Iran which has a long history in oil production, can lead to significant damages to surface and subsurface structures, and requires serious consideration.

A Deep Learning Approach Based on Graphs to Detect Plantation Lines

no code implementations5 Feb 2021 Diogo Nunes Gonçalves, Mauro dos Santos de Arruda, Hemerson Pistori, Vanessa Jordão Marcato Fernandes, Ana Paula Marques Ramos, Danielle Elis Garcia Furuya, Lucas Prado Osco, Hongjie He, Jonathan Li, José Marcato Junior, Wesley Nunes Gonçalves

This feature map is used as an input to the Knowledge Estimation Module (KEM), organized in three concatenated branches for detecting 1) the plant positions, 2) the plantation lines, and 3) for the displacement vectors between the plants.

OpenGF: An Ultra-Large-Scale Ground Filtering Dataset Built Upon Open ALS Point Clouds Around the World

1 code implementation24 Jan 2021 Nannan Qin, Weikai Tan, Lingfei Ma, Dedong Zhang, Jonathan Li

Ground filtering has remained a widely studied but incompletely resolved bottleneck for decades in the automatic generation of high-precision digital elevation model, due to the dramatic changes of topography and the complex structures of objects.

3D Semantic Segmentation Scene Understanding

A Review on Deep Learning in UAV Remote Sensing

no code implementations22 Jan 2021 Lucas Prado Osco, José Marcato Junior, Ana Paula Marques Ramos, Lúcio André de Castro Jorge, Sarah Narges Fatholahi, Jonathan de Andrade Silva, Edson Takashi Matsubara, Hemerson Pistori, Wesley Nunes Gonçalves, Jonathan Li

In the remote sensing field, surveys and literature revisions specifically involving DNNs algorithms' applications have been conducted in an attempt to summarize the amount of information produced in its subfields.

Time Series Analysis

A CNN Approach to Simultaneously Count Plants and Detect Plantation-Rows from UAV Imagery

no code implementations31 Dec 2020 Lucas Prado Osco, Mauro dos Santos de Arruda, Diogo Nunes Gonçalves, Alexandre Dias, Juliana Batistoti, Mauricio de Souza, Felipe David Georges Gomes, Ana Paula Marques Ramos, Lúcio André de Castro Jorge, Veraldo Liesenberg, Jonathan Li, Lingfei Ma, José Marcato Junior, Wesley Nunes Gonçalves

In the corn plantation datasets (with both growth phases, young and mature), our approach returned a mean absolute error (MAE) of 6. 224 plants per image patch, a mean relative error (MRE) of 0. 1038, precision and recall values of 0. 856, and 0. 905, respectively, and an F-measure equal to 0. 876.

Climbing the WOL: Training for Cheaper Inference

no code implementations2 Jul 2020 Zichang Liu, Zhaozhuo Xu, Alan Ji, Jonathan Li, Beidi Chen, Anshumali Shrivastava

Efficient inference for wide output layers (WOLs) is an essential yet challenging task in large scale machine learning.


Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Review

no code implementations20 May 2020 Ying Li, Lingfei Ma, Zilong Zhong, Fei Liu, Dongpu Cao, Jonathan Li, Michael A. Chapman

In this paper, we provide a systematic review of existing compelling deep learning architectures applied in LiDAR point clouds, detailing for specific tasks in autonomous driving such as segmentation, detection, and classification.

3D Semantic Segmentation Autonomous Driving +4

Toronto-3D: A Large-scale Mobile LiDAR Dataset for Semantic Segmentation of Urban Roadways

1 code implementation18 Mar 2020 Weikai Tan, Nannan Qin, Lingfei Ma, Ying Li, Jing Du, Guorong Cai, Ke Yang, Jonathan Li

Semantic segmentation of large-scale outdoor point clouds is essential for urban scene understanding in various applications, especially autonomous driving and urban high-definition (HD) mapping.

Autonomous Driving Scene Understanding +2

Deep convolutional neural network application on rooftop detection for aerial image

no code implementations29 Oct 2019 Mengge Chen, Jonathan Li

As one of the most destructive disasters in the world, earthquake causes death, injuries, destruction and enormous damage to the affected area.

PipeMare: Asynchronous Pipeline Parallel DNN Training

no code implementations9 Oct 2019 Bowen Yang, Jian Zhang, Jonathan Li, Christopher Ré, Christopher R. Aberger, Christopher De Sa

Pipeline parallelism (PP) when training neural networks enables larger models to be partitioned spatially, leading to both lower network communication and overall higher hardware utilization.

Squeeze-and-Attention Networks for Semantic Segmentation

1 code implementation CVPR 2020 Zilong Zhong, Zhong Qiu Lin, Rene Bidart, Xiaodan Hu, Ibrahim Ben Daya, Zhifeng Li, Wei-Shi Zheng, Jonathan Li, Alexander Wong

The recent integration of attention mechanisms into segmentation networks improves their representational capabilities through a great emphasis on more informative features.

Segmentation Semantic Segmentation

Toward better boundary preserved supervoxel segmentation for 3D point clouds

1 code implementation ISPRS Journal of Photogrammetry and Remote Sensing 2019 Yangbin Lin, Cheng Wang, Dawei Zhai, Wei Li, Jonathan Li

In this paper, we present a simple but effective supervoxel segmentation method for point clouds, which formalizes supervoxel segmentation as a subset selection problem.

Point Cloud Segmentation Segmentation

PointNLM: Point Nonlocal-Means for vegetation segmentation based on middle echo point clouds

no code implementations20 Jun 2019 Jonathan Li, Rongren Wu, Yiping Chen, Qing Zhu, Zhipeng Luo, Cheng Wang

Second, to accurately extract trees from all point clouds, we propose a 3D deep learning network, PointNLM, to semantically segment tree crowns.

Point Cloud Segmentation Segmentation +1

RF-Net: An End-to-End Image Matching Network based on Receptive Field

1 code implementation CVPR 2019 Xuelun Shen, Cheng Wang, Xin Li, Zenglei Yu, Jonathan Li, Chenglu Wen, Ming Cheng, Zijian He

This paper proposes a new end-to-end trainable matching network based on receptive field, RF-Net, to compute sparse correspondence between images.

Keypoint Detection

Fast Regularity-Constrained Plane Reconstruction

no code implementations20 May 2019 Yangbin Lin, Jialian Li, Cheng Wang, Zhonggui Chen, Zongyue Wang, Jonathan Li

Man-made environments typically comprise planar structures that exhibit numerous geometric relationships, such as parallelism, coplanarity, and orthogonality.

Generative Adversarial Networks and Conditional Random Fields for Hyperspectral Image Classification

no code implementations12 May 2019 Zilong Zhong, Jonathan Li, David A. Clausi, Alexander Wong

In this paper, we address the hyperspectral image (HSI) classification task with a generative adversarial network and conditional random field (GAN-CRF) -based framework, which integrates a semi-supervised deep learning and a probabilistic graphical model, and make three contributions.

Classification General Classification +2

NeuroTreeNet: A New Method to Explore Horizontal Expansion Network

no code implementations22 Nov 2018 Shenlong Lou, Yan Luo, Qiancong Fan, Feng Chen, Yiping Chen, Cheng Wang, Jonathan Li

It is widely recognized that the deeper networks or networks with more feature maps have better performance.


Layerwise Recurrent Autoencoder for General Real-world Traffic Flow Forecasting

no code implementations27 Sep 2018 Peize Zhao, Danfeng Cai, Shaokun Zhang, Feng Chen, Zhemin Zhang, Cheng Wang, Jonathan Li

To forecast the traffic flow across a wide area and overcome the mentioned challenges, we design and propose a promising forecasting model called Layerwise Recurrent Autoencoder (LRA), in which a three-layer stacked autoencoder (SAE) architecture is used to obtain temporal traffic correlations and a recurrent neural networks (RNNs) model for prediction.


Geometric Multi-Model Fitting by Deep Reinforcement Learning

no code implementations22 Sep 2018 Zongliang Zhang, Hongbin Zeng, Jonathan Li, Yiping Chen, Chenhui Yang, Cheng Wang

This paper deals with the geometric multi-model fitting from noisy, unstructured point set data (e. g., laser scanned point clouds).

Decision Making reinforcement-learning +1

Generative Adversarial Networks and Probabilistic Graph Models for Hyperspectral Image Classification

no code implementations10 Feb 2018 Zilong Zhong, Jonathan Li

High spectral dimensionality and the shortage of annotations make hyperspectral image (HSI) classification a challenging problem.

Classification General Classification +1

Traffic Sign Timely Visual Recognizability Evaluation Based on 3D Measurable Point Clouds

no code implementations10 Oct 2017 Shanxin Zhang, Cheng Wang, Zhuang Yang, Chenglu Wen, Jonathan Li, Chenhui Yang

Then, based on the VEM, we proposed the concept of the Visual Recognizability Field (VRF) to reflect the visual recognizability distribution in 3D space and established a Visual Recognizability Evaluation Model (VREM) to measure a traffic sign visual recognizability for a given viewpoint.

Point Cloud Segmentation

Partial Procedural Geometric Model Fitting for Point Clouds

1 code implementation17 Oct 2016 Zongliang Zhang, Jonathan Li, Yulan Guo, Yangbin Lin, Ming Cheng, Cheng Wang

However, most geometric model fitting methods are unable to fit an arbitrary geometric model (e. g. a surface with holes) to incomplete data, due to that the similarity metrics used in these methods are unable to measure the rigid partial similarity between arbitrary models.

Robust Scene Text Recognition Using Sparse Coding based Features

no code implementations29 Dec 2015 Da-Han Wang, Hanzi Wang, Dong Zhang, Jonathan Li, David Zhang

For character detection, we use the HSC features instead of using the Histograms of Oriented Gradients (HOG) features.

Scene Text Recognition

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