arXiv subjects

Jonathan Li

Publications and source records attributed to Jonathan Li.

At least 73 records · Page 4Linked to original sources

arXiv2023

Prefix Propagation: Parameter-Efficient Tuning for Long Sequences

Parameter-efficient tuning aims to mitigate the large memory requirements of adapting pretrained language models for downstream tasks. For example, one popular method, prefix-tuning, prepends trainable tokens to sequences while freezing the rest of the model's parameters. Although such models attain comparable performance with fine-tuning when applied to sequences with short to moderate lengths, we show their inferior performance when modelling long sequences. To bridge this gap, we propose prefix-propagation, a simple but effective approach that conditions prefixes on previous hidden states. We empirically demonstrate that prefix-propagation outperforms prefix-tuning across long-document tasks, while using 50% fewer parameters. To further investigate the proposed architecture, we also show its advantage in calibration, and perform additional study on its relationship with kernel attention. To the best of our knowledge, this work is the first to focus on parameter-efficient learning for long-sequence language tasks.

cs.CL↗

arXiv2023

MTLSegFormer: Multi-task Learning with Transformers for Semantic Segmentation in Precision Agriculture

Multi-task learning has proven to be effective in improving the performance of correlated tasks. Most of the existing methods use a backbone to extract initial features with independent branches for each task, and the exchange of information between the branches usually occurs through the concatenation or sum of the feature maps of the branches. However, this type of information exchange does not directly consider the local characteristics of the image nor the level of importance or correlation between the tasks. In this paper, we propose a semantic segmentation method, MTLSegFormer, which combines multi-task learning and attention mechanisms. After the backbone feature extraction, two feature maps are learned for each task. The first map is proposed to learn features related to its task, while the second map is obtained by applying learned visual attention to locally re-weigh the feature maps of the other tasks. In this way, weights are assigned to local regions of the image of other tasks that have greater importance for the specific task. Finally, the two maps are combined and used to solve a task. We tested the performance in two challenging problems with correlated tasks and observed a significant improvement in accuracy, mainly in tasks with high dependence on the others.

cs.CV↗

arXiv2022

Parameter-Efficient Legal Domain Adaptation

Seeking legal advice is often expensive. Recent advancements in machine learning for solving complex problems can be leveraged to help make legal services more accessible to the public. However, real-life applications encounter significant challenges. State-of-the-art language models are growing increasingly large, making parameter-efficient learning increasingly important. Unfortunately, parameter-efficient methods perform poorly with small amounts of data, which are common in the legal domain (where data labelling costs are high). To address these challenges, we propose parameter-efficient legal domain adaptation, which uses vast unsupervised legal data from public legal forums to perform legal pre-training. This method exceeds or matches the fewshot performance of existing models such as LEGAL-BERT on various legal tasks while tuning only approximately 0.1% of model parameters. Additionally, we show that our method can achieve calibration comparable to existing methods across several tasks. To the best of our knowledge, this work is among the first to explore parameter-efficient methods of tuning language models in the legal domain.

cs.CL↗

arXiv2022

Transformers in 3D Point Clouds: A Survey

Transformers have been at the heart of the Natural Language Processing (NLP) and Computer Vision (CV) revolutions. The significant success in NLP and CV inspired exploring the use of Transformers in point cloud processing. However, how do Transformers cope with the irregularity and unordered nature of point clouds? How suitable are Transformers for different 3D representations (e.g., point- or voxel-based)? How competent are Transformers for various 3D processing tasks? As of now, there is still no systematic survey of the research on these issues. For the first time, we provided a comprehensive overview of increasingly popular Transformers for 3D point cloud analysis. We start by introducing the theory of the Transformer architecture and reviewing its applications in 2D/3D fields. Then, we present three different taxonomies (i.e., implementation-, data representation-, and task-based), which can classify current Transformer-based methods from multiple perspectives. Furthermore, we present the results of an investigation of the variants and improvements of the self-attention mechanism in 3D. 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. Finally, we suggest three potential research directions, providing benefit references for the development of 3D Transformers.

cs.CV↗

arXiv2022

CF-YOLO: Cross Fusion YOLO for Object Detection in Adverse Weather with a High-quality Real Snow Dataset

Snow is one of the toughest adverse weather conditions for object detection (OD). Currently, not only there is a lack of snowy OD datasets to train cutting-edge detectors, but also these detectors have difficulties learning latent information beneficial for detection in snow. To alleviate the two above problems, we first establish a real-world snowy OD dataset, named RSOD. Besides, we develop an unsupervised training strategy with a distinctive activation function, called $Peak \ Act$, to quantitatively evaluate the effect of snow on each object. Peak Act helps grading the images in RSOD into four-difficulty levels. To our knowledge, RSOD is the first quantitatively evaluated and graded snowy OD dataset. Then, we propose a novel Cross Fusion (CF) block to construct a lightweight OD network based on YOLOv5s (call CF-YOLO). CF is a plug-and-play feature aggregation module, which integrates the advantages of Feature Pyramid Network and Path Aggregation Network in a simpler yet more flexible form. Both RSOD and CF lead our CF-YOLO to possess an optimization ability for OD in real-world snow. That is, CF-YOLO can handle unfavorable detection problems of vagueness, distortion and covering of snow. Experiments show that our CF-YOLO achieves better detection results on RSOD, compared to SOTAs. The code and dataset are available at https://github.com/qqding77/CF-YOLO-and-RSOD.

cs.CV↗

arXiv2022

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

Although accurate and fast point cloud classification is a fundamental task in 3D applications, it is difficult to achieve this purpose due to the irregularity and disorder of point clouds that make it challenging to achieve effective and efficient global discriminative feature learning. Lately, 3D Transformers have been adopted to improve point cloud processing. Nevertheless, massive Transformer layers tend to incur huge computational and memory costs. 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. Our method has two main modules operating on the downsampling point sets, and each module consists of a multi-scale local feature aggregating (LFA) block and a global feature learning (GFL) block, which are implemented by using Graph Convolution and Transformer respectively. We also conduct a detailed investigation on a series of Transformer variants to explore better performance for our network. Various experiments on ModelNet40 demonstrate that our method achieves state-of-the-art classification performance, in terms of both accuracy and efficiency.

cs.CV↗

arXiv2022

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

Learning dense point-wise semantics from unstructured 3D point clouds with fewer labels, although a realistic problem, has been under-explored in literature. While existing weakly supervised methods can effectively learn semantics with only a small fraction of point-level annotations, we find that the vanilla bounding box-level annotation is also informative for semantic segmentation of large-scale 3D point clouds. In this paper, we introduce a neural architecture, termed Box2Seg, to learn point-level semantics of 3D point clouds with bounding box-level supervision. The key to our approach is to generate accurate pseudo labels by exploring the geometric and topological structure inside and outside each bounding box. Specifically, an attention-based self-training (AST) technique and Point Class Activation Mapping (PCAM) are utilized to estimate pseudo-labels. The network is further trained and refined with pseudo labels. Experiments on two large-scale benchmarks including S3DIS and ScanNet demonstrate the competitive performance of the proposed method. In particular, the proposed network can be trained with cheap, or even off-the-shelf bounding box-level annotations and subcloud-level tags.

cs.CV↗

arXiv2021

The impact of data volume on performance of deep learning based building rooftop extraction using very high spatial resolution aerial images

Building rooftop data are of importance in several urban applications and in natural disaster management. In contrast to traditional surveying and mapping, by using high spatial resolution aerial images, deep learning-based building rooftops extraction methods are efficient and accurate. Although more training data is preferred in deep learning-based tasks, the effect of data volume on building extraction models is underexplored. Therefore, the paper explores the impact of data volume on the performance of building rooftop extraction from very-high-spatial-resolution (VHSR) images using deep learning-based methods. To do so, we manually labelled 0.12m spatial resolution aerial images and perform a comparative analysis of models trained on datasets of different sizes using popular deep learning architectures for segmentation tasks, including Fully Convolutional Networks (FCN)-8s, U-Net and DeepLabv3+. The experiments showed that with more training data, algorithms converged faster and achieved higher accuracy, while better algorithms were able to better mitigate the lack of training data.

cs.CV↗

arXiv2021

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

We present a novel direction-aware feature-level frequency decomposition network for single image deraining. Compared with existing solutions, the proposed network has three compelling characteristics. First, unlike previous algorithms, we propose to perform frequency decomposition at feature-level instead of image-level, allowing both low-frequency maps containing structures and high-frequency maps containing details to be continuously refined during the training procedure. 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. Third, different from existing algorithms using convolutional filters consistent in all directions, we propose a direction-aware filter to capture the direction of rain streaks in order to more effectively and thoroughly purge the input images of rain streaks. We extensively evaluate the proposed approach in three representative datasets and experimental results corroborate our approach consistently outperforms state-of-the-art deraining algorithms.

cs.CV↗

arXiv2021

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

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. The recent breakthrough of supervised deep learning algorithms in 3D scene understanding brings new solutions for better solving such problems. However, there are few large-scale and scene-rich public datasets dedicated to ground extraction, which considerably limits the development of effective deep-learning-based ground filtering methods. To this end, we present OpenGF, first Ultra-Large-Scale Ground Filtering dataset covering over 47 $km^2$ of 9 different typical terrain scenes built upon open ALS point clouds of 4 different countries around the world. OpenGF contains more than half a billion finely labeled ground and non-ground points, thousands of times the number of labeled points than the de facto standard ISPRS filtertest dataset. We extensively evaluate the performance of state-of-the-art rule-based algorithms and 3D semantic segmentation networks on our dataset and provide a comprehensive analysis. The results have confirmed the capability of OpenGF to train deep learning models effectively. This dataset is released at https://github.com/Nathan-UW/OpenGF to promote more advancing research for ground filtering and large-scale 3D geographic environment understanding.

cs.CV↗

arXiv2021

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

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. In this study, the Small BAseline Subset (SBAS) approach, which is a multi-temporal Interferometric Synthetic Aperture Radar (InSAR) algorithm was employed to resolve ground deformation in the Marun region, Iran. A total of 22 interferograms were generated using 10 Envisat ASAR images. The mean velocity map obtained in the Line-Of-Sight (LOS) direction of satellite to the ground reveals the maximum subsidence on order of 13.5 mm per year over the field due to both tectonic and non-tectonic features. In order to assess the effect of non-tectonic features such as petroleum extraction on ground surface displacement, the results of InSAR have been compared with the oil production rate, which have shown a good agreement.

eess.IV↗

arXiv2021

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

In this paper, we propose a novel deep learning method based on a Convolutional Neural Network (CNN) that simultaneously detects and geolocates plantation-rows while counting its plants considering highly-dense plantation configurations. The experimental setup was evaluated in a cornfield with different growth stages and in a Citrus orchard. Both datasets characterize different plant density scenarios, locations, types of crops, sensors, and dates. A two-branch architecture was implemented in our CNN method, where the information obtained within the plantation-row is updated into the plant detection branch and retro-feed to the row branch; which are then refined by a Multi-Stage Refinement method. 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. These results were superior to the results from other deep networks (HRNet, Faster R-CNN, and RetinaNet) evaluated with the same task and dataset. For the plantation-row detection, our approach returned precision, recall, and F-measure scores of 0.913, 0.941, and 0.925, respectively. To test the robustness of our model with a different type of agriculture, we performed the same task in the citrus orchard dataset. It returned an MAE equal to 1.409 citrus-trees per patch, MRE of 0.0615, precision of 0.922, recall of 0.911, and F-measure of 0.965. For citrus plantation-row detection, our approach resulted in precision, recall, and F-measure scores equal to 0.965, 0.970, and 0.964, respectively. The proposed method achieved state-of-the-art performance for counting and geolocating plants and plant-rows in UAV images from different types of crops.

cs.CV↗

arXiv2021

Counting and Locating High-Density Objects Using Convolutional Neural Network

This paper presents a Convolutional Neural Network (CNN) approach for counting and locating objects in high-density imagery. To the best of our knowledge, this is the first object counting and locating method based on a feature map enhancement and a Multi-Stage Refinement of the confidence map. The proposed method was evaluated in two counting datasets: tree and car. For the tree dataset, our method returned a mean absolute error (MAE) of 2.05, a root-mean-squared error (RMSE) of 2.87 and a coefficient of determination (R$^2$) of 0.986. For the car dataset (CARPK and PUCPR+), our method was superior to state-of-the-art methods. In the these datasets, our approach achieved an MAE of 4.45 and 3.16, an RMSE of 6.18 and 4.39, and an R$^2$ of 0.975 and 0.999, respectively. The proposed method is suitable for dealing with high object-density, returning a state-of-the-art performance for counting and locating objects.

cs.CV↗

arXiv2021

Semantic Segmentation with Labeling Uncertainty and Class Imbalance

Recently, methods based on Convolutional Neural Networks (CNN) achieved impressive success in semantic segmentation tasks. However, challenges such as the class imbalance and the uncertainty in the pixel-labeling process are not completely addressed. As such, we present a new approach that calculates a weight for each pixel considering its class and uncertainty during the labeling process. The pixel-wise weights are used during training to increase or decrease the importance of the pixels. Experimental results show that the proposed approach leads to significant improvements in three challenging segmentation tasks in comparison to baseline methods. It was also proved to be more invariant to noise. The approach presented here may be used within a wide range of semantic segmentation methods to improve their robustness.

cs.CV↗

arXiv2021

A Deep Learning Approach Based on Graphs to Detect Plantation Lines

Deep learning-based networks are among the most prominent methods to learn linear patterns and extract this type of information from diverse imagery conditions. Here, we propose a deep learning approach based on graphs to detect plantation lines in UAV-based RGB imagery presenting a challenging scenario containing spaced plants. The first module of our method extracts a feature map throughout the backbone, which consists of the initial layers of the VGG16. 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. A graph modeling is applied considering each plant position on the image as vertices, and edges are formed between two vertices (i.e. plants). Finally, the edge is classified as pertaining to a certain plantation line based on three probabilities (higher than 0.5): i) in visual features obtained from the backbone; ii) a chance that the edge pixels belong to a line, from the KEM step; and iii) an alignment of the displacement vectors with the edge, also from KEM. Experiments were conducted in corn plantations with different growth stages and patterns with aerial RGB imagery. A total of 564 patches with 256 x 256 pixels were used and randomly divided into training, validation, and testing sets in a proportion of 60\%, 20\%, and 20\%, respectively. The proposed method was compared against state-of-the-art deep learning methods, and achieved superior performance with a significant margin, returning precision, recall, and F1-score of 98.7\%, 91.9\%, and 95.1\%, respectively. This approach is useful in extracting lines with spaced plantation patterns and could be implemented in scenarios where plantation gaps occur, generating lines with few-to-none interruptions.

cs.CV↗

arXiv2020

UAV LiDAR Point Cloud Segmentation of A Stack Interchange with Deep Neural Networks

Stack interchanges are essential components of transportation systems. Mobile laser scanning (MLS) systems have been widely used in road infrastructure mapping, but accurate mapping of complicated multi-layer stack interchanges are still challenging. This study examined the point clouds collected by a new Unmanned Aerial Vehicle (UAV) Light Detection and Ranging (LiDAR) system to perform the semantic segmentation task of a stack interchange. An end-to-end supervised 3D deep learning framework was proposed to classify the point clouds. The proposed method has proven to capture 3D features in complicated interchange scenarios with stacked convolution and the result achieved over 93% classification accuracy. In addition, the new low-cost semi-solid-state LiDAR sensor Livox Mid-40 featuring a incommensurable rosette scanning pattern has demonstrated its potential in high-definition urban mapping.

cs.CV↗

arXiv2020

Climbing the WOL: Training for Cheaper Inference

Efficient inference for wide output layers (WOLs) is an essential yet challenging task in large scale machine learning. Most approaches reduce this problem to approximate maximum inner product search (MIPS), which relies heavily on the observation that for a given model, ground truth labels correspond to logits of highest value during full model inference. However, such an assumption is restrictive in practice. In this paper, we argue that approximate MIPS subroutines, despite having sub-linear computation time, are sub-optimal because they are tailored for retrieving large inner products with high recall instead of retrieving the correct labels. With WOL, the labels often have moderate inner products, which makes approximate MIPS more challenging. We propose an alternative problem formulation, called Label Superior Sampling (LSS), where the objective is to tailor the system to ensure retrieval of the correct label. Accordingly, we propose a novel learned hash approach, which is significantly more efficient and sufficient for high inference accuracy than MIPS baselines. Our extensive evaluation indicates that LSS can match or even outperform full inference accuracy with around 5x speed up and 87% energy reduction.

cs.IR↗

arXiv2020

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

Recently, the advancement of deep learning in discriminative feature learning from 3D LiDAR data has led to rapid development in the field of autonomous driving. However, automated processing uneven, unstructured, noisy, and massive 3D point clouds is a challenging and tedious task. 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. Although several published research papers focus on specific topics in computer vision for autonomous vehicles, to date, no general survey on deep learning applied in LiDAR point clouds for autonomous vehicles exists. Thus, the goal of this paper is to narrow the gap in this topic. More than 140 key contributions in the recent five years are summarized in this survey, including the milestone 3D deep architectures, the remarkable deep learning applications in 3D semantic segmentation, object detection, and classification; specific datasets, evaluation metrics, and the state of the art performance. Finally, we conclude the remaining challenges and future researches.

cs.CV↗