arXiv subjects

Haoyu Dong

Publications and source records attributed to Haoyu Dong.

At least 73 records · Page 4Linked to original sources

arXiv2023

A systematic study of the foreground-background imbalance problem in deep learning for object detection

The class imbalance problem in deep learning has been explored in several studies, but there has yet to be a systematic analysis of this phenomenon in object detection. Here, we present comprehensive analyses and experiments of the foreground-background (F-B) imbalance problem in object detection, which is very common and caused by small, infrequent objects of interest. We experimentally study the effects of different aspects of F-B imbalance (object size, number of objects, dataset size, object type) on detection performance. In addition, we also compare 9 leading methods for addressing this problem, including Faster-RCNN, SSD, OHEM, Libra-RCNN, Focal-Loss, GHM, PISA, YOLO-v3, and GFL with a range of datasets from different imaging domains. We conclude that (1) the F-B imbalance can indeed cause a significant drop in detection performance, (2) The detection performance is more affected by F-B imbalance when fewer training data are available, (3) in most cases, decreasing object size leads to larger performance drop than decreasing number of objects, given the same change in the ratio of object pixels to non-object pixels, (6) among all selected methods, Libra-RCNN and PISA demonstrate the best performance in addressing the issue of F-B imbalance. (7) When the training dataset size is large, the choice of method is not impactful (8) Soft-sampling methods, including focal-loss, GHM, and GFL, perform fairly well on average but are relatively unstable.

cs.CV↗

arXiv2023

Segment Anything Model for Medical Image Analysis: an Experimental Study

Training segmentation models for medical images continues to be challenging due to the limited availability of data annotations. Segment Anything Model (SAM) is a foundation model that is intended to segment user-defined objects of interest in an interactive manner. While the performance on natural images is impressive, medical image domains pose their own set of challenges. Here, we perform an extensive evaluation of SAM's ability to segment medical images on a collection of 19 medical imaging datasets from various modalities and anatomies. We report the following findings: (1) SAM's performance based on single prompts highly varies depending on the dataset and the task, from IoU=0.1135 for spine MRI to IoU=0.8650 for hip X-ray. (2) Segmentation performance appears to be better for well-circumscribed objects with prompts with less ambiguity and poorer in various other scenarios such as the segmentation of brain tumors. (3) SAM performs notably better with box prompts than with point prompts. (4) SAM outperforms similar methods RITM, SimpleClick, and FocalClick in almost all single-point prompt settings. (5) When multiple-point prompts are provided iteratively, SAM's performance generally improves only slightly while other methods' performance improves to the level that surpasses SAM's point-based performance. We also provide several illustrations for SAM's performance on all tested datasets, iterative segmentation, and SAM's behavior given prompt ambiguity. We conclude that SAM shows impressive zero-shot segmentation performance for certain medical imaging datasets, but moderate to poor performance for others. SAM has the potential to make a significant impact in automated medical image segmentation in medical imaging, but appropriate care needs to be applied when using it.

cs.CV↗

arXiv2023

Electronic Janus lattice and kagome-like bands in coloring-triangular MoTe2 monolayers

Polymorphic structures of transition-metal dichalcogenides (TMDs) host exotic electronic states, like charge density wave and superconductivity. However, the number of these structures is limited by crystal symmetries, which poses a challenge to achieve tailored lattices and properties both theoretically and experimentally. Here, we report a coloring-triangle (CT) latticed MoTe2 monolayer, termed CT-MoTe2, constructed by controllably introducing uniform and ordered mirror-twin-boundaries into a pristine monolayer in molecular beam epitaxy. Low-temperature scanning tunneling microscopy and spectroscopy (STM/STS) together with theoretical calculations reveal that the monolayer has an electronic Janus lattice, i.e., an energy-dependent atomic-lattice and a pseudo-Te sublattice, and shares the identical geometry with the Mo5Te8 layer. Dirac-like and flat electronic bands inherently existing in the CT lattice are identified by two broad and two prominent peaks in STS spectra, respectively, and verified with density-functional-theory calculations. Two types of intrinsic domain boundaries were observed, in one of which the electronic-Janus-lattice feature maintains, implying potential applications as an energy-tunable electron-tunneling barrier in future functional devices.

cond-mat.mtrl-sci↗

arXiv2023

Emergent Electronic Kagome Lattice in Correlated Charge-Density-Wave State of 1T-TaS$_2$

Quantum materials with tunable correlated and/or topological electronic states, such as the electronic Kagome lattice, provide an ideal platform to study the exotic quantum properties. However, the real-space investigations on the correlated electronic Kagome lattice have been rarely reported. Herein, we report on the electronic Kagome lattice emerging in the correlated charge-density-wave (CDW) state of 1T-TaS$_2$ at ~200 K via variable-temperature scanning tunneling microscopy (VT-STM). This emergent Kagome lattice can be considered a fractional electron-filling superstructure with reduced translational and rotational symmetries, confirmed by STM measurements and density functional theory simulations. The characteristic band structure and density of states of this electronic Kagome lattice are further explored based on theoretical calculations. Our results demonstrate a self-organized electronic Kagome lattice from the correlated CDW state via the effective tuning parameter of temperature and provide a platform to directly explore the interplay of correlated electrons and topological physics.

cond-mat.mtrl-sci↗

arXiv2022

PLOG: Table-to-Logic Pretraining for Logical Table-to-Text Generation

Logical table-to-text generation is a task that involves generating logically faithful sentences from tables, which requires models to derive logical level facts from table records via logical inference. It raises a new challenge on the logical-level content planning of table-to-text models. However, directly learning the logical inference knowledge from table-text pairs is very difficult for neural models because of the ambiguity of natural language and the scarcity of parallel data. Hence even large-scale pre-trained language models present low logical fidelity on logical table-to-text. In this work, we propose a PLOG (Pretrained Logical Form Generator) framework to improve the generation fidelity. Specifically, PLOG is first pretrained on a table-to-logic-form generation (table-to-logic) task, then finetuned on downstream table-to-text tasks. The formal definition of logical forms enables us to collect large amount of accurate logical forms from tables without human annotation. In addition, PLOG can learn logical inference from table-logic pairs much more definitely than from table-text pairs. To evaluate our model, we further collect a controlled logical table-to-text dataset CONTLOG based on an existing dataset. On two benchmarks, LOGICNLG and CONTLOG, PLOG outperforms strong baselines by a large margin on the logical fidelity, demonstrating the effectiveness of table-to-logic pretraining.

cs.CL↗

arXiv2022

Reflection of Thought: Inversely Eliciting Numerical Reasoning in Language Models via Solving Linear Systems

Numerical reasoning over natural language has been a long-standing goal for the research community. However, cutting-edge language models have proven difficult to reliably generalize to a broad range of numbers, although they have shown proficiency in reasoning over common and simple numbers. In this paper, we propose a novel method to elicit and exploit the numerical reasoning knowledge hidden in pre-trained language models using simple anchor numbers. Concretely, we first leverage simple numbers as anchors to probe the implicitly inferred arithmetic expressions from language models, and then explicitly apply the expressions on complex numbers to get corresponding answers. To inversely elicit arithmetic expressions, we transform and formulate the task as an analytically solvable linear system. Experimental results on several numerical reasoning benchmarks demonstrate that our approach significantly improves numerical reasoning capabilities of existing LMs. More importantly, our approach is training-free and simply works in the inference phase, making it highly portable and achieving consistent performance benefits across a variety of language models (GPT-3, T5, BART, etc) in all zero-shot, few-shot, and fine-tuning scenarios.

cs.CL↗

arXiv2022

Lightweight Transformer Backbone for Medical Object Detection

Lesion detection in digital breast tomosynthesis (DBT) is an important and a challenging problem characterized by a low prevalence of images containing tumors. Due to the label scarcity problem, large deep learning models and computationally intensive algorithms are likely to fail when applied to this task. In this paper, we present a practical yet lightweight backbone to improve the accuracy of tumor detection. Specifically, we propose a novel modification of visual transformer (ViT) on image feature patches to connect the feature patches of a tumor with healthy backgrounds of breast images and form a more robust backbone for tumor detection. To the best of our knowledge, our model is the first work of Transformer backbone object detection for medical imaging. Our experiments show that this model can considerably improve the accuracy of lesion detection and reduce the amount of labeled data required in typical ViT. We further show that with additional augmented tumor data, our model significantly outperforms the Faster R-CNN model and state-of-the-art SWIN transformer model.

cs.CV↗

arXiv2022

The Intrinsic Manifolds of Radiological Images and their Role in Deep Learning

The manifold hypothesis is a core mechanism behind the success of deep learning, so understanding the intrinsic manifold structure of image data is central to studying how neural networks learn from the data. Intrinsic dataset manifolds and their relationship to learning difficulty have recently begun to be studied for the common domain of natural images, but little such research has been attempted for radiological images. We address this here. First, we compare the intrinsic manifold dimensionality of radiological and natural images. We also investigate the relationship between intrinsic dimensionality and generalization ability over a wide range of datasets. Our analysis shows that natural image datasets generally have a higher number of intrinsic dimensions than radiological images. However, the relationship between generalization ability and intrinsic dimensionality is much stronger for medical images, which could be explained as radiological images having intrinsic features that are more difficult to learn. These results give a more principled underpinning for the intuition that radiological images can be more challenging to apply deep learning to than natural image datasets common to machine learning research. We believe rather than directly applying models developed for natural images to the radiological imaging domain, more care should be taken to developing architectures and algorithms that are more tailored to the specific characteristics of this domain. The research shown in our paper, demonstrating these characteristics and the differences from natural images, is an important first step in this direction.

eess.IV↗

arXiv2022

TaCube: Pre-computing Data Cubes for Answering Numerical-Reasoning Questions over Tabular Data

Existing auto-regressive pre-trained language models (PLMs) like T5 and BART, have been well applied to table question answering by UNIFIEDSKG and TAPEX, respectively, and demonstrated state-of-the-art results on multiple benchmarks. However, auto-regressive PLMs are challenged by recent emerging numerical reasoning datasets, such as TAT-QA, due to the error-prone implicit calculation. In this paper, we present TaCube, to pre-compute aggregation/arithmetic results for the table in advance, so that they are handy and readily available for PLMs to answer numerical reasoning questions. TaCube systematically and comprehensively covers a collection of computational operations over table segments. By simply concatenating TaCube to the input sequence of PLMs, it shows significant experimental effectiveness. TaCube promotes the F1 score from 49.6% to 66.2% on TAT-QA and achieves new state-of-the-art results on WikiTQ (59.6% denotation accuracy). TaCube's improvements on numerical reasoning cases are even more notable: on TAT-QA, TaCube promotes the exact match accuracy of BART-large by 39.6% on sum, 52.5% on average, 36.6% on substraction, and 22.2% on division. We believe that TaCube is a general and portable pre-computation solution that can be potentially integrated to various numerical reasoning frameworks

cs.IR↗

arXiv2022

Table Pre-training: A Survey on Model Architectures, Pre-training Objectives, and Downstream Tasks

Since a vast number of tables can be easily collected from web pages, spreadsheets, PDFs, and various other document types, a flurry of table pre-training frameworks have been proposed following the success of text and images, and they have achieved new state-of-the-arts on various tasks such as table question answering, table type recognition, column relation classification, table search, formula prediction, etc. To fully use the supervision signals in unlabeled tables, a variety of pre-training objectives have been designed and evaluated, for example, denoising cell values, predicting numerical relationships, and implicitly executing SQLs. And to best leverage the characteristics of (semi-)structured tables, various tabular language models, particularly with specially-designed attention mechanisms, have been explored. Since tables usually appear and interact with free-form text, table pre-training usually takes the form of table-text joint pre-training, which attracts significant research interests from multiple domains. This survey aims to provide a comprehensive review of different model designs, pre-training objectives, and downstream tasks for table pre-training, and we further share our thoughts and vision on existing challenges and future opportunities.

cs.CL↗

arXiv2022

HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generation

Tables are often created with hierarchies, but existing works on table reasoning mainly focus on flat tables and neglect hierarchical tables. Hierarchical tables challenge existing methods by hierarchical indexing, as well as implicit relationships of calculation and semantics. This work presents HiTab, a free and open dataset to study question answering (QA) and natural language generation (NLG) over hierarchical tables. HiTab is a cross-domain dataset constructed from a wealth of statistical reports (analyses) and Wikipedia pages, and has unique characteristics: (1) nearly all tables are hierarchical, and (2) both target sentences for NLG and questions for QA are revised from original, meaningful, and diverse descriptive sentences authored by analysts and professions of reports. (3) to reveal complex numerical reasoning in statistical analyses, we provide fine-grained annotations of entity and quantity alignment. HiTab provides 10,686 QA pairs and descriptive sentences with well-annotated quantity and entity alignment on 3,597 tables with broad coverage of table hierarchies and numerical reasoning types. Targeting hierarchical structure, we devise a novel hierarchy-aware logical form for symbolic reasoning over tables, which shows high effectiveness. Targeting complex numerical reasoning, we propose partially supervised training given annotations of entity and quantity alignment, which helps models to largely reduce spurious predictions in the QA task. In the NLG task, we find that entity and quantity alignment also helps NLG models to generate better results in a conditional generation setting. Experiment results of state-of-the-art baselines suggest that this dataset presents a strong challenge and a valuable benchmark for future research.

cs.CL↗

arXiv2022

FORTAP: Using Formulas for Numerical-Reasoning-Aware Table Pretraining

Tables store rich numerical data, but numerical reasoning over tables is still a challenge. In this paper, we find that the spreadsheet formula, which performs calculations on numerical values in tables, is naturally a strong supervision of numerical reasoning. More importantly, large amounts of spreadsheets with expert-made formulae are available on the web and can be obtained easily. FORTAP is the first method for numerical-reasoning-aware table pretraining by leveraging large corpus of spreadsheet formulae. We design two formula pretraining tasks to explicitly guide FORTAP to learn numerical reference and calculation in semi-structured tables. FORTAP achieves state-of-the-art results on two representative downstream tasks, cell type classification and formula prediction, showing great potential of numerical-reasoning-aware pretraining.

cs.IR↗

arXiv2022

Twisted Angle-Dependent Work Functions in CVD-Grown Twisted Bilayer Graphene by Kelvin Probe Force Microscopy

Tailoring the interlayer twist angle of bilayer graphene (BLG) has a significant influence on its electronic properties, including superconductivity, topological transitions, ferromagnetic states and correlated insulating states. These exotic electronic properties are sensitively dependent on the work functions of bilayer graphene samples. Here, the twisted angle-dependent work functions of CVD-grown twisted bilayer graphene (tBLG) are detailed investigated by Kelvin Probe Force Microscopy (KPFM) in combination with Raman spectra. The thickness-dependent surface potentials of Bernal-stacked multilayer graphene were measured. The AB-BLG and tBLG are directly determined by KPFM due to their twist angle-specific surface potentials. The detailed relationship of twist angles and surface potentials are further obtained by the in-situ combination investigation of KPFM and Raman spectra measurements. The thermal stability of tBLG was further explored through controlled annealing process. Our work provides the twisted angle-dependent surface potentials of tBLG and lays the foundation for further exploring their twist-angle-dependent novel electronic properties.

cond-mat.mtrl-sci↗

arXiv2022

Trust It or Not: Confidence-Guided Automatic Radiology Report Generation

Medical imaging plays a pivotal role in diagnosis and treatment in clinical practice. Inspired by the significant progress in automatic image captioning, various deep learning (DL)-based methods have been proposed to generate radiology reports for medical images. Despite promising results, previous works overlook the uncertainties of their models and are thus unable to provide clinicians with the reliability/confidence of the generated radiology reports to assist their decision-making. In this paper, we propose a novel method to explicitly quantify both the visual uncertainty and the textual uncertainty for DL-based radiology report generation. Such multi-modal uncertainties can sufficiently capture the model confidence degree at both the report level and the sentence level, and thus they are further leveraged to weight the losses for more comprehensive model optimization. Experimental results have demonstrated that the proposed method for model uncertainty characterization and estimation can produce more reliable confidence scores for radiology report generation, and the modified loss function, which takes into account the uncertainties, leads to better model performance on two public radiology report datasets. In addition, the quality of the automatically generated reports was manually evaluated by human raters and the results also indicate that the proposed uncertainties can reflect the variance of clinical diagnosis.

cs.CV↗

arXiv2021

TUTA: Tree-based Transformers for Generally Structured Table Pre-training

Tables are widely used with various structures to organize and present data. Recent attempts on table understanding mainly focus on relational tables, yet overlook to other common table structures. In this paper, we propose TUTA, a unified pre-training architecture for understanding generally structured tables. Noticing that understanding a table requires spatial, hierarchical, and semantic information, we enhance transformers with three novel structure-aware mechanisms. First, we devise a unified tree-based structure, called a bi-dimensional coordinate tree, to describe both the spatial and hierarchical information of generally structured tables. Upon this, we propose tree-based attention and position embedding to better capture the spatial and hierarchical information. Moreover, we devise three progressive pre-training objectives to enable representations at the token, cell, and table levels. We pre-train TUTA on a wide range of unlabeled web and spreadsheet tables and fine-tune it on two critical tasks in the field of table structure understanding: cell type classification and table type classification. Experiments show that TUTA is highly effective, achieving state-of-the-art on five widely-studied datasets.

cs.IR↗

arXiv2021

TableSense: Spreadsheet Table Detection with Convolutional Neural Networks

Spreadsheet table detection is the task of detecting all tables on a given sheet and locating their respective ranges. Automatic table detection is a key enabling technique and an initial step in spreadsheet data intelligence. However, the detection task is challenged by the diversity of table structures and table layouts on the spreadsheet. Considering the analogy between a cell matrix as spreadsheet and a pixel matrix as image, and encouraged by the successful application of Convolutional Neural Networks (CNN) in computer vision, we have developed TableSense, a novel end-to-end framework for spreadsheet table detection. First, we devise an effective cell featurization scheme to better leverage the rich information in each cell; second, we develop an enhanced convolutional neural network model for table detection to meet the domain-specific requirement on precise table boundary detection; third, we propose an effective uncertainty metric to guide an active learning based smart sampling algorithm, which enables the efficient build-up of a training dataset with 22,176 tables on 10,220 sheets with broad coverage of diverse table structures and layouts. Our evaluation shows that TableSense is highly effective with 91.3\% recall and 86.5\% precision in EoB-2 metric, a significant improvement over both the current detection algorithm that are used in commodity spreadsheet tools and state-of-the-art convolutional neural networks in computer vision.

cs.IR↗

arXiv2021

Epitaxial fabrication of AgTe monolayer on Ag(111) and the sequential growth of Te film

Transition-metal chalcogenides (TMCs) materials have attracted increasing interest both for fundamental research and industrial applications. Among all these materials, two-dimensional (2D) compounds with honeycomb-like structure possess exotic electronic structures. Here, we report a systematic study of TMC monolayer AgTe fabricated by direct depositing Te on the surface of Ag(111) and annealing. Few intrinsic defects are observed and studied by scanning tunneling microscopy, indicating that there are two kinds of AgTe domains and they can form gliding twin-boundary. Then, the monolayer AgTe can serve as the template for the following growth of Te film. Meanwhile, some Te atoms are observed in the form of chains on the top of the bottom Te film. Our findings in this work might provide insightful guide for the epitaxial growth of 2D materials for study of novel physical properties and for future quantum devices.

cond-mat.mtrl-sci↗

arXiv2021

Toplayer-Dependent Crystallographic Orientation Imaging in the Bilayer Two-Dimensional Materials with Transverse Shear Microscopy

Nanocontact properties of two-dimensional (2D) materials are closely dependent on their unique nanomechanical systems, such as the number of atomic layers and the supporting substrate. Here, we report a direct observation of toplayer-dependent crystallographic orientation imaging of 2D materials with the transverse shear microscopy (TSM). Three typical nanomechanical systems, MoS2 on the amorphous SiO2/Si, graphene on the amorphous SiO2/Si, and MoS2 on the crystallized Al2O3, have been investigated in detail. This experimental observation reveals that puckering behaviour mainly occurs on the top layer of 2D materials, which is attributed to its direct contact adhesion with the AFM tip. Furthermore, the result of crystallographic orientation imaging of MoS2/SiO2/Si and MoS2/Al2O3 indicated that the underlying crystalline substrates almost do not contribute to the puckering effect of 2D materials. Our work directly revealed the top layer dependent puckering properties of 2D material, and demonstrate the general applications of TSM in the bilayer 2D systems.

cond-mat.mtrl-sci↗