arXiv subjects

Seunghyun Park

Publications and source records attributed to Seunghyun Park.

35 records · Page 2Linked to original sources

arXiv2022

OCR-free Document Understanding Transformer

Understanding document images (e.g., invoices) is a core but challenging task since it requires complex functions such as reading text and a holistic understanding of the document. Current Visual Document Understanding (VDU) methods outsource the task of reading text to off-the-shelf Optical Character Recognition (OCR) engines and focus on the understanding task with the OCR outputs. Although such OCR-based approaches have shown promising performance, they suffer from 1) high computational costs for using OCR; 2) inflexibility of OCR models on languages or types of document; 3) OCR error propagation to the subsequent process. To address these issues, in this paper, we introduce a novel OCR-free VDU model named Donut, which stands for Document understanding transformer. As the first step in OCR-free VDU research, we propose a simple architecture (i.e., Transformer) with a pre-training objective (i.e., cross-entropy loss). Donut is conceptually simple yet effective. Through extensive experiments and analyses, we show a simple OCR-free VDU model, Donut, achieves state-of-the-art performances on various VDU tasks in terms of both speed and accuracy. In addition, we offer a synthetic data generator that helps the model pre-training to be flexible in various languages and domains. The code, trained model and synthetic data are available at https://github.com/clovaai/donut.

cs.LG↗

arXiv2022

Evidence for strong progenitor age dependence of type Ia supernova luminosity standardization process

Supernova (SN) cosmology is based on the assumption that the width-luminosity relation (WLR) and the color-luminosity relation (CLR) in the type Ia SN luminosity standardization would not show {absolute magnitude differences} with progenitor age. Unlike this expectation, recent age datings of stellar populations in host galaxies have shown significant correlations between progenitor age and Hubble residual (HR). Here we show that this correlation originates from a strong progenitor age dependence of the zero-points of the WLR and the CLR, in the sense that SNe from younger progenitors are fainter each at given light-curve parameters $x_1$ and $c$. This $4.6σ$ result is reminiscent of Baade's discovery of the zero-point variation of the Cepheid period-luminosity relation with age, and, as such, causes a serious systematic bias with redshift in SN cosmology. Other host properties show substantially smaller and insignificant offsets in the WLR and CLR for the same dataset. We illustrate that the differences between the high-$z$ and low-$z$ SNe in the WLR and CLR, and in HR after the standardization, are fully comparable to those between the correspondingly young and old SNe at intermediate redshift, indicating that the observed dimming of SNe with redshift may well be an artifact of over-correction in the luminosity standardization. When this systematic bias with redshift is properly taken into account, there is little evidence left for an accelerating universe, in discordance with other probes, urging the follow-up investigations with larger samples at different redshift bins.

astro-ph.GA↗

arXiv2022

Grounding Visual Representations with Texts for Domain Generalization

Reducing the representational discrepancy between source and target domains is a key component to maximize the model generalization. In this work, we advocate for leveraging natural language supervision for the domain generalization task. We introduce two modules to ground visual representations with texts containing typical reasoning of humans: (1) Visual and Textual Joint Embedder and (2) Textual Explanation Generator. The former learns the image-text joint embedding space where we can ground high-level class-discriminative information into the model. The latter leverages an explainable model and generates explanations justifying the rationale behind its decision. To the best of our knowledge, this is the first work to leverage the vision-and-language cross-modality approach for the domain generalization task. Our experiments with a newly created CUB-DG benchmark dataset demonstrate that cross-modality supervision can be successfully used to ground domain-invariant visual representations and improve the model generalization. Furthermore, in the large-scale DomainBed benchmark, our proposed method achieves state-of-the-art results and ranks 1st in average performance for five multi-domain datasets. The dataset and codes are available at https://github.com/mswzeus/GVRT.

cs.CV↗

arXiv2022

An Embedding-Dynamic Approach to Self-supervised Learning

A number of recent self-supervised learning methods have shown impressive performance on image classification and other tasks. A somewhat bewildering variety of techniques have been used, not always with a clear understanding of the reasons for their benefits, especially when used in combination. Here we treat the embeddings of images as point particles and consider model optimization as a dynamic process on this system of particles. Our dynamic model combines an attractive force for similar images, a locally dispersive force to avoid local collapse, and a global dispersive force to achieve a globally-homogeneous distribution of particles. The dynamic perspective highlights the advantage of using a delayed-parameter image embedding (a la BYOL) together with multiple views of the same image. It also uses a purely-dynamic local dispersive force (Brownian motion) that shows improved performance over other methods and does not require knowledge of other particle coordinates. The method is called MSBReg which stands for (i) a Multiview centroid loss, which applies an attractive force to pull different image view embeddings toward their centroid, (ii) a Singular value loss, which pushes the particle system toward spatially homogeneous density, (iii) a Brownian diffusive loss. We evaluate downstream classification performance of MSBReg on ImageNet as well as transfer learning tasks including fine-grained classification, multi-class object classification, object detection, and instance segmentation. In addition, we also show that applying our regularization term to other methods further improves their performance and stabilize the training by preventing a mode collapse.

cs.CV↗

arXiv2022

DEER: Detection-agnostic End-to-End Recognizer for Scene Text Spotting

Recent end-to-end scene text spotters have achieved great improvement in recognizing arbitrary-shaped text instances. Common approaches for text spotting use region of interest pooling or segmentation masks to restrict features to single text instances. However, this makes it hard for the recognizer to decode correct sequences when the detection is not accurate i.e. one or more characters are cropped out. Considering that it is hard to accurately decide word boundaries with only the detector, we propose a novel Detection-agnostic End-to-End Recognizer, DEER, framework. The proposed method reduces the tight dependency between detection and recognition modules by bridging them with a single reference point for each text instance, instead of using detected regions. The proposed method allows the decoder to recognize the texts that are indicated by the reference point, with features from the whole image. Since only a single point is required to recognize the text, the proposed method enables text spotting without an arbitrarily-shaped detector or bounding polygon annotations. Experimental results present that the proposed method achieves competitive results on regular and arbitrarily-shaped text spotting benchmarks. Further analysis shows that DEER is robust to the detection errors. The code and dataset will be publicly available.

cs.CV↗

arXiv2022

Semi-Structured Query Grounding for Document-Oriented Databases with Deep Retrieval and Its Application to Receipt and POI Matching

Semi-structured query systems for document-oriented databases have many real applications. One particular application that we are interested in is matching each financial receipt image with its corresponding place of interest (POI, e.g., restaurant) in the nationwide database. The problem is especially challenging in the real production environment where many similar or incomplete entries exist in the database and queries are noisy (e.g., errors in optical character recognition). In this work, we aim to address practical challenges when using embedding-based retrieval for the query grounding problem in semi-structured data. Leveraging recent advancements in deep language encoding for retrieval, we conduct extensive experiments to find the most effective combination of modules for the embedding and retrieval of both query and database entries without any manually engineered component. The proposed model significantly outperforms the conventional manual pattern-based model while requiring much less development and maintenance cost. We also discuss some core observations in our experiments, which could be helpful for practitioners working on a similar problem in other domains.

cs.IR↗

arXiv2021

SWAD: Domain Generalization by Seeking Flat Minima

Domain generalization (DG) methods aim to achieve generalizability to an unseen target domain by using only training data from the source domains. Although a variety of DG methods have been proposed, a recent study shows that under a fair evaluation protocol, called DomainBed, the simple empirical risk minimization (ERM) approach works comparable to or even outperforms previous methods. Unfortunately, simply solving ERM on a complex, non-convex loss function can easily lead to sub-optimal generalizability by seeking sharp minima. In this paper, we theoretically show that finding flat minima results in a smaller domain generalization gap. We also propose a simple yet effective method, named Stochastic Weight Averaging Densely (SWAD), to find flat minima. SWAD finds flatter minima and suffers less from overfitting than does the vanilla SWA by a dense and overfit-aware stochastic weight sampling strategy. SWAD shows state-of-the-art performances on five DG benchmarks, namely PACS, VLCS, OfficeHome, TerraIncognita, and DomainNet, with consistent and large margins of +1.6% averagely on out-of-domain accuracy. We also compare SWAD with conventional generalization methods, such as data augmentation and consistency regularization methods, to verify that the remarkable performance improvements are originated from by seeking flat minima, not from better in-domain generalizability. Last but not least, SWAD is readily adaptable to existing DG methods without modification; the combination of SWAD and an existing DG method further improves DG performances. Source code is available at https://github.com/khanrc/swad.

cs.LG↗

arXiv2021

Pre-Training of Deep Bidirectional Protein Sequence Representations with Structural Information

Bridging the exponentially growing gap between the numbers of unlabeled and labeled protein sequences, several studies adopted semi-supervised learning for protein sequence modeling. In these studies, models were pre-trained with a substantial amount of unlabeled data, and the representations were transferred to various downstream tasks. Most pre-training methods solely rely on language modeling and often exhibit limited performance. In this paper, we introduce a novel pre-training scheme called PLUS, which stands for Protein sequence representations Learned Using Structural information. PLUS consists of masked language modeling and a complementary protein-specific pre-training task, namely same-family prediction. PLUS can be used to pre-train various model architectures. In this work, we use PLUS to pre-train a bidirectional recurrent neural network and refer to the resulting model as PLUS-RNN. Our experiment results demonstrate that PLUS-RNN outperforms other models of similar size solely pre-trained with the language modeling in six out of seven widely used protein biology tasks. Furthermore, we present the results from our qualitative interpretation analyses to illustrate the strengths of PLUS-RNN. PLUS provides a novel way to exploit evolutionary relationships among unlabeled proteins and is broadly applicable across a variety of protein biology tasks. We expect that the gap between the numbers of unlabeled and labeled proteins will continue to grow exponentially, and the proposed pre-training method will play a larger role.

q-bio.BM↗

arXiv2021

Spatial Dependency Parsing for Semi-Structured Document Information Extraction

Information Extraction (IE) for semi-structured document images is often approached as a sequence tagging problem by classifying each recognized input token into one of the IOB (Inside, Outside, and Beginning) categories. However, such problem setup has two inherent limitations that (1) it cannot easily handle complex spatial relationships and (2) it is not suitable for highly structured information, which are nevertheless frequently observed in real-world document images. To tackle these issues, we first formulate the IE task as spatial dependency parsing problem that focuses on the relationship among text tokens in the documents. Under this setup, we then propose SPADE (SPAtial DEpendency parser) that models highly complex spatial relationships and an arbitrary number of information layers in the documents in an end-to-end manner. We evaluate it on various kinds of documents such as receipts, name cards, forms, and invoices, and show that it achieves a similar or better performance compared to strong baselines including BERT-based IOB taggger.

cs.CL↗

arXiv2021

SelfReg: Self-supervised Contrastive Regularization for Domain Generalization

In general, an experimental environment for deep learning assumes that the training and the test dataset are sampled from the same distribution. However, in real-world situations, a difference in the distribution between two datasets, domain shift, may occur, which becomes a major factor impeding the generalization performance of the model. The research field to solve this problem is called domain generalization, and it alleviates the domain shift problem by extracting domain-invariant features explicitly or implicitly. In recent studies, contrastive learning-based domain generalization approaches have been proposed and achieved high performance. These approaches require sampling of the negative data pair. However, the performance of contrastive learning fundamentally depends on quality and quantity of negative data pairs. To address this issue, we propose a new regularization method for domain generalization based on contrastive learning, self-supervised contrastive regularization (SelfReg). The proposed approach use only positive data pairs, thus it resolves various problems caused by negative pair sampling. Moreover, we propose a class-specific domain perturbation layer (CDPL), which makes it possible to effectively apply mixup augmentation even when only positive data pairs are used. The experimental results show that the techniques incorporated by SelfReg contributed to the performance in a compatible manner. In the recent benchmark, DomainBed, the proposed method shows comparable performance to the conventional state-of-the-art alternatives. Codes are available at https://github.com/dnap512/SelfReg.

cs.CV↗

arXiv2020

Kagome van-der-Waals Pd3P2S8 with flat band

With the advanced investigations into low-dimensional systems, it has become essential to find materials having interesting lattices that can be exfoliated down to monolayer. One particular important structure is a kagome lattice with its potentially diverse and vibrant physics. We report a van-der-Waals kagome lattice material, Pd3P2S8, with several unique properties such as an intriguing flat band. The flat band is shown to arise from a possible compact-localized state of all five 4d orbitals of Pd. The diamagnetic susceptibility is precisely measured to support the calculated susceptibility obtained from the band structure. We further demonstrate that Pd3P2S8 can be exfoliated down to monolayer, which ultimately will allow the possible control of the localized states in this two-dimensional kagome lattice using the electric field gating.

cond-mat.mtrl-sci↗

arXiv2020

Syntactic Question Abstraction and Retrieval for Data-Scarce Semantic Parsing

Deep learning approaches to semantic parsing require a large amount of labeled data, but annotating complex logical forms is costly. Here, we propose Syntactic Question Abstraction and Retrieval (SQAR), a method to build a neural semantic parser that translates a natural language (NL) query to a SQL logical form (LF) with less than 1,000 annotated examples. SQAR first retrieves a logical pattern from the train data by computing the similarity between NL queries and then grounds a lexical information on the retrieved pattern in order to generate the final LF. We validate SQAR by training models using various small subsets of WikiSQL train data achieving up to 4.9% higher LF accuracy compared to the previous state-of-the-art models on WikiSQL test set. We also show that by using query-similarity to retrieve logical pattern, SQAR can leverage a paraphrasing dataset achieving up to 5.9% higher LF accuracy compared to the case where SQAR is trained by using only WikiSQL data. In contrast to a simple pattern classification approach, SQAR can generate unseen logical patterns upon the addition of new examples without re-training the model. We also discuss an ideal way to create cost efficient and robust train datasets when the data distribution can be approximated under a data-hungry setting.

cs.CL↗

arXiv2020

SquidLab -- a user-friendly program for background subtraction and fitting of magnetization data

We present an open-source program free to download for academic use with full user-friendly graphical interface for performing flexible and robust background subtraction and dipole fitting on magnetization data. For magnetic samples with small moment sizes or sample environments with large or asymmetric magnetic backgrounds, it can become necessary to separate background and sample contributions to each measured raw voltage measurement before fitting the dipole signal to extract magnetic moments. Originally designed for use with pressure cells on a Quantum Design MPMS3 SQUID magnetometer, SquidLab is a modular object-oriented platform implemented in Matlab with a range of importers for different widely-available magnetometer systems (including MPMS, MPMS-XL, MPMS-IQuantum, MPMS3 and S700X models), and has been tested with a broad variety of background and signal types. The software allows background subtraction of baseline signals, signal preprocessing, and performing fits to dipole data using Levenberg-Marquadt non-linear least squares, or a singular value decomposition linear algebra algorithm which excels at picking out noisy or weak dipole signals. A plugin system allows users to easily extend the built-in functionality with their own importers, processes or fitting algorithms. SquidLab can be downloaded, under Academic License, from the University of Warwick depository (wrap.warwick.ac.uk/129665).

physics.data-an↗

arXiv2019

A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualization

We present SQLova, the first Natural-language-to-SQL (NL2SQL) model to achieve human performance in WikiSQL dataset. We revisit and discuss diverse popular methods in NL2SQL literature, take a full advantage of BERT {Devlin et al., 2018) through an effective table contextualization method, and coherently combine them, outperforming the previous state of the art by 8.2% and 2.5% in logical form and execution accuracy, respectively. We particularly note that BERT with a seq2seq decoder leads to a poor performance in the task, indicating the importance of a careful design when using such large pretrained models. We also provide a comprehensive analysis on the dataset and our model, which can be helpful for designing future NL2SQL datsets and models. We especially show that our model's performance is near the upper bound in WikiSQL, where we observe that a large portion of the evaluation errors are due to wrong annotations, and our model is already exceeding human performance by 1.3% in execution accuracy.

cs.CL↗

arXiv2016

deepTarget: End-to-end Learning Framework for microRNA Target Prediction using Deep Recurrent Neural Networks

MicroRNAs (miRNAs) are short sequences of ribonucleic acids that control the expression of target messenger RNAs (mRNAs) by binding them. Robust prediction of miRNA-mRNA pairs is of utmost importance in deciphering gene regulations but has been challenging because of high false positive rates, despite a deluge of computational tools that normally require laborious manual feature extraction. This paper presents an end-to-end machine learning framework for miRNA target prediction. Leveraged by deep recurrent neural networks-based auto-encoding and sequence-sequence interaction learning, our approach not only delivers an unprecedented level of accuracy but also eliminates the need for manual feature extraction. The performance gap between the proposed method and existing alternatives is substantial (over 25% increase in F-measure), and deepTarget delivers a quantum leap in the long-standing challenge of robust miRNA target prediction.

cs.LG↗

arXiv2016

deepMiRGene: Deep Neural Network based Precursor microRNA Prediction

Since microRNAs (miRNAs) play a crucial role in post-transcriptional gene regulation, miRNA identification is one of the most essential problems in computational biology. miRNAs are usually short in length ranging between 20 and 23 base pairs. It is thus often difficult to distinguish miRNA-encoding sequences from other non-coding RNAs and pseudo miRNAs that have a similar length, and most previous studies have recommended using precursor miRNAs instead of mature miRNAs for robust detection. A great number of conventional machine-learning-based classification methods have been proposed, but they often have the serious disadvantage of requiring manual feature engineering, and their performance is limited as well. In this paper, we propose a novel miRNA precursor prediction algorithm, deepMiRGene, based on recurrent neural networks, specifically long short-term memory networks. deepMiRGene automatically learns suitable features from the data themselves without manual feature engineering and constructs a model that can successfully reflect structural characteristics of precursor miRNAs. For the performance evaluation of our approach, we have employed several widely used evaluation metrics on three recent benchmark datasets and verified that deepMiRGene delivered comparable performance among the current state-of-the-art tools.

cs.LG↗

arXiv2011

HiTRACE: High-throughput robust analysis for capillary electrophoresis

Motivation: Capillary electrophoresis (CE) of nucleic acids is a workhorse technology underlying high-throughput genome analysis and large-scale chemical mapping for nucleic acid structural inference. Despite the wide availability of CE-based instruments, there remain challenges in leveraging their full power for quantitative analysis of RNA and DNA structure, thermodynamics, and kinetics. In particular, the slow rate and poor automation of available analysis tools have bottlenecked a new generation of studies involving hundreds of CE profiles per experiment. Results: We propose a computational method called high-throughput robust analysis for capillary electrophoresis (HiTRACE) to automate the key tasks in large-scale nucleic acid CE analysis, including the profile alignment that has heretofore been a rate-limiting step in the highest throughput experiments. We illustrate the application of HiTRACE on thirteen data sets representing 4 different RNAs, three chemical modification strategies, and up to 480 single mutant variants; the largest data sets each include 87,360 bands. By applying a series of robust dynamic programming algorithms, HiTRACE outperforms prior tools in terms of alignment and fitting quality, as assessed by measures including the correlation between quantified band intensities between replicate data sets. Furthermore, while the smallest of these data sets required 7 to 10 hours of manual intervention using prior approaches, HiTRACE quantitation of even the largest data sets herein was achieved in 3 to 12 minutes. The HiTRACE method therefore resolves a critical barrier to the efficient and accurate analysis of nucleic acid structure in experiments involving tens of thousands of electrophoretic bands.

q-bio.QM↗