73 citations · 123 across the 14 of their papers we have counts for
17 papers
Bounded Hyperbolic Tangent: A Stable and Efficient Alternative to Pre-Layer Normalization in Large Language Models
Hoyoon Byun, Youngjun Choi, Taero Kim +2
Pre-Layer Normalization (Pre-LN) is the de facto choice for large language models (LLMs) and is crucial for stable pretraining and effective transfer learning. However, Pre-LN incu…
SRFormer: Text Detection Transformer with Incorporated Segmentation and Regression
Qingwen Bu, Sungrae Park, Minsoo Khang +1
Existing techniques for text detection can be broadly classified into two primary groups: segmentation-based and regression-based methods. Segmentation models offer enhanced robust…
Domain Generalization by Mutual-Information Regularization with Pre-trained Models
Junbum Cha, Kyungjae Lee, Sungrae Park +1
Domain generalization (DG) aims to learn a generalized model to an unseen target domain using only limited source domains. Previous attempts to DG fail to learn domain-invariant re…
Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features
Byeonghu Na, Yoonsik Kim, Sungrae Park
Linguistic knowledge has brought great benefits to scene text recognition by providing semantics to refine character sequences. However, since linguistic knowledge has been applied…
BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents
Teakgyu Hong, Donghyun Kim, Mingi Ji +3
Key information extraction (KIE) from document images requires understanding the contextual and spatial semantics of texts in two-dimensional (2D) space. Many recent studies try to…
SynthTIGER: Synthetic Text Image GEneratoR Towards Better Text Recognition Models
Moonbin Yim, Yoonsik Kim, Han-Cheol Cho +1
For successful scene text recognition (STR) models, synthetic text image generators have alleviated the lack of annotated text images from the real world. Specifically, they genera…
RewriteNet: Reliable Scene Text Editing with Implicit Decomposition of Text Contents and Styles
Junyeop Lee, Yoonsik Kim, Seonghyeon Kim +4
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 betwe…
Show, Attend and Distill:Knowledge Distillation via Attention-based Feature Matching
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. Most studies manually tie intermediate featu…
SWAD: Domain Generalization by Seeking Flat Minima
Junbum Cha, Sanghyuk Chun, Kyungjae Lee +4
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…
Character Region Attention For Text Spotting
Youngmin Baek, Seung Shin, Jeonghun Baek +4
A scene text spotter is composed of text detection and recognition modules. Many studies have been conducted to unify these modules into an end-to-end trainable model to achieve be…
CLEval: Character-Level Evaluation for Text Detection and Recognition Tasks
Youngmin Baek, Daehyun Nam, Sungrae Park +5
Despite the recent success of text detection and recognition methods, existing evaluation metrics fail to provide a fair and reliable comparison among those methods. In addition, t…
On Recognizing Texts of Arbitrary Shapes with 2D Self-Attention
Junyeop Lee, Sungrae Park, Jeonghun Baek +3
Scene text recognition (STR) is the task of recognizing character sequences in natural scenes. While there have been great advances in STR methods, current methods still fail to re…
Hierarchical Context enabled Recurrent Neural Network for Recommendation
Kyungwoo Song, Mingi Ji, Sungrae Park +1
A long user history inevitably reflects the transitions of personal interests over time. The analyses on the user history require the robust sequential model to anticipate the tran…
Adversarial Dropout for Recurrent Neural Networks
Sungrae Park, Kyungwoo Song, Mingi Ji +2
Successful application processing sequential data, such as text and speech, requires an improved generalization performance of recurrent neural networks (RNNs). Dropout techniques…
What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis
Jeonghun Baek, Geewook Kim, Junyeop Lee +5
Many new proposals for scene text recognition (STR) models have been introduced in recent years. While each claim to have pushed the boundary of the technology, a holistic and fair…
Dirichlet Variational Autoencoder
Weonyoung Joo, Wonsung Lee, Sungrae Park +1
This paper proposes Dirichlet Variational Autoencoder (DirVAE) using a Dirichlet prior for a continuous latent variable that exhibits the characteristic of the categorical probabil…
Adversarial Dropout for Supervised and Semi-supervised Learning
Sungrae Park, Jun-Keon Park, Su-Jin Shin +1
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 per…