Search Results for author: Sungrae Park

Found 19 papers, 15 papers with code

Domain Generalization by Mutual-Information Regularization with Pre-trained Models

1 code implementation21 Mar 2022 Junbum Cha, Kyungjae Lee, Sungrae Park, Sanghyuk Chun

Domain generalization (DG) aims to learn a generalized model to an unseen target domain using only limited source domains.

Domain Generalization

Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features

1 code implementation30 Nov 2021 Byeonghu Na, Yoonsik Kim, Sungrae Park

Furthermore, MATRN stimulates combining semantic features into visual features by hiding visual clues related to the character in the training phase.

Scene Text Recognition

RewriteNet: Reliable Scene Text Editing with Implicit Decomposition of Text Contents and Styles

no code implementations23 Jul 2021 Junyeop Lee, Yoonsik Kim, Seonghyeon Kim, Moonbin Yim, Seung Shin, Gayoung Lee, Sungrae Park

Scene text editing (STE), which converts a text in a scene image into the desired text while preserving an original style, is a challenging task due to a complex intervention between text and style.

Image Generation Scene Text Editing +1

SynthTIGER: Synthetic Text Image GEneratoR Towards Better Text Recognition Models

1 code implementation20 Jul 2021 Moonbin Yim, Yoonsik Kim, Han-Cheol Cho, Sungrae Park

For successful scene text recognition (STR) models, synthetic text image generators have alleviated the lack of annotated text images from the real world.

Image Generation Scene Text Recognition

SWAD: Domain Generalization by Seeking Flat Minima

3 code implementations NeurIPS 2021 Junbum Cha, Sanghyuk Chun, Kyungjae Lee, Han-Cheol Cho, Seunghyun Park, Yunsung Lee, Sungrae Park

Domain generalization (DG) methods aim to achieve generalizability to an unseen target domain by using only training data from the source domains.

Domain Generalization Generalization Bounds +1

Show, Attend and Distill:Knowledge Distillation via Attention-based Feature Matching

1 code implementation5 Feb 2021 Mingi Ji, Byeongho Heo, Sungrae Park

Knowledge distillation extracts general knowledge from a pre-trained teacher network and provides guidance to a target student network.

General Knowledge Knowledge Distillation +2

BROS: A Pre-trained Language Model for Understanding Texts in Document

no code implementations1 Jan 2021 Teakgyu Hong, Donghyun Kim, Mingi Ji, Wonseok Hwang, Daehyun Nam, Sungrae Park

Although the recent advance in OCR enables the accurate extraction of text segments, it is still challenging to extract key information from documents due to the diversity of layouts.

Document Layout Analysis Language Modelling +1

Character Region Attention For Text Spotting

no code implementations ECCV 2020 Youngmin Baek, Seung Shin, Jeonghun Baek, Sungrae Park, Junyeop Lee, Daehyun Nam, Hwalsuk Lee

This architecture is formed by utilizing detection outputs in the recognizer and propagating the recognition loss through the detection stage.

Text Spotting

CLEval: Character-Level Evaluation for Text Detection and Recognition Tasks

1 code implementation11 Jun 2020 Youngmin Baek, Daehyun Nam, Sungrae Park, Junyeop Lee, Seung Shin, Jeonghun Baek, Chae Young Lee, Hwalsuk Lee

We believe that our metrics can play a key role in developing and analyzing state-of-the-art text detection and recognition methods.

Optical Character Recognition

Group-Transformer: Towards A Lightweight Character-level Language Model

no code implementations25 Sep 2019 Sungrae Park, Geewook Kim, Junyeop Lee, Junbum Cha, Ji-Hoon Kim Hwalsuk Lee

When compared to Transformers with a comparable number of parameters and time complexity, the proposed model shows better performance.

Language Modelling

Hierarchical Context enabled Recurrent Neural Network for Recommendation

1 code implementation26 Apr 2019 Kyungwoo Song, Mingi Ji, Sungrae Park, Il-Chul Moon

The analyses on the user history require the robust sequential model to anticipate the transitions and the decays of user interests.

Sequential Recommendation

Adversarial Dropout for Recurrent Neural Networks

2 code implementations22 Apr 2019 Sungrae Park, Kyungwoo Song, Mingi Ji, Wonsung Lee, Il-Chul Moon

Successful application processing sequential data, such as text and speech, requires an improved generalization performance of recurrent neural networks (RNNs).

Language Modelling Semi-Supervised Text Classification

Dirichlet Variational Autoencoder

1 code implementation ICLR 2019 Weonyoung Joo, Wonsung Lee, Sungrae Park, Il-Chul Moon

The experimental results show that 1) DirVAE models the latent representation result with the best log-likelihood compared to the baselines; and 2) DirVAE produces more interpretable latent values with no collapsing issues which the baseline models suffer from.

General Classification Topic Models

Adversarial Dropout for Supervised and Semi-supervised Learning

3 code implementations12 Jul 2017 Sungrae Park, Jun-Keon Park, Su-Jin Shin, Il-Chul Moon

Recently, the training with adversarial examples, which are generated by adding a small but worst-case perturbation on input examples, has been proved to improve generalization performance of neural networks.

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