Search Results for author: Byungsoo Ko

Found 15 papers, 10 papers with code

VVS: Video-to-Video Retrieval with Irrelevant Frame Suppression

1 code implementation15 Mar 2023 Won Jo, Geuntaek Lim, Gwangjin Lee, Hyunwoo Kim, Byungsoo Ko, Yukyung Choi

In content-based video retrieval (CBVR), dealing with large-scale collections, efficiency is as important as accuracy; thus, several video-level feature-based studies have actively been conducted.

Retrieval Video Retrieval

Group Generalized Mean Pooling for Vision Transformer

no code implementations8 Dec 2022 Byungsoo Ko, Han-Gyu Kim, Byeongho Heo, Sangdoo Yun, Sanghyuk Chun, Geonmo Gu, Wonjae Kim

As ViT groups the channels via a multi-head attention mechanism, grouping the channels by GGeM leads to lower head-wise dependence while amplifying important channels on the activation maps.

Image Retrieval Representation Learning +1

DialogCC: Large-Scale Multi-Modal Dialogue Dataset

no code implementations8 Dec 2022 Young-Jun Lee, Byungsoo Ko, Han-Gyu Kim, Ho-Jin Choi

As sharing images in an instant message is a crucial factor, there has been active research on learning a image-text multi-modal dialogue model.

Retrieval Text Retrieval

Granularity-aware Adaptation for Image Retrieval over Multiple Tasks

no code implementations5 Oct 2022 Jon Almazán, Byungsoo Ko, Geonmo Gu, Diane Larlus, Yannis Kalantidis

We address it with the proposed Grappa, an approach that starts from a strong pretrained model, and adapts it to tackle multiple retrieval tasks concurrently, using only unlabeled images from the different task domains.

Image Retrieval Pseudo Label +2

Large-scale Bilingual Language-Image Contrastive Learning

1 code implementation28 Mar 2022 Byungsoo Ko, Geonmo Gu

This paper is a technical report to share our experience and findings building a Korean and English bilingual multimodal model.

Contrastive Learning Proper Noun +1

Towards Light-weight and Real-time Line Segment Detection

2 code implementations1 Jun 2021 Geonmo Gu, Byungsoo Ko, SeoungHyun Go, Sung-Hyun Lee, Jingeun Lee, Minchul Shin

In this paper, we propose a real-time and light-weight line segment detector for resource-constrained environments named Mobile LSD (M-LSD).

Line Segment Detection Real-Time Object Detection

Learning with Memory-based Virtual Classes for Deep Metric Learning

1 code implementation ICCV 2021 Byungsoo Ko, Geonmo Gu, Han-Gyu Kim

This can be undesirable for DML, where training and test data exhibit entirely different classes.

Metric Learning

Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learning

2 code implementations29 Mar 2021 Geonmo Gu, Byungsoo Ko, Han-Gyu Kim

One of the main purposes of deep metric learning is to construct an embedding space that has well-generalized embeddings on both seen (training) classes and unseen (test) classes.

Image Retrieval Metric Learning +1

An Effective Pipeline for a Real-world Clothes Retrieval System

no code implementations26 May 2020 Yang-Ho Ji, HeeJae Jun, Insik Kim, Jongtack Kim, Youngjoon Kim, Byungsoo Ko, Hyong-Keun Kook, Jingeun Lee, Sangwon Lee, Sanghyuk Park

In this paper, we propose an effective pipeline for clothes retrieval system which has sturdiness on large-scale real-world fashion data.

Metric Learning Retrieval

Embedding Expansion: Augmentation in Embedding Space for Deep Metric Learning

2 code implementations CVPR 2020 Byungsoo Ko, Geonmo Gu

Meanwhile, post-processing techniques, such as query expansion and database augmentation, have proposed the combination of feature points to obtain additional semantic information.

Clustering Image Retrieval +2

Symmetrical Synthesis for Deep Metric Learning

1 code implementation31 Jan 2020 Geonmo Gu, Byungsoo Ko

Secondly, it performs hard negative pair mining within the original and synthetic points to select a more informative negative pair for computing the metric learning loss.

Clustering Image Retrieval +4

A Benchmark on Tricks for Large-scale Image Retrieval

no code implementations27 Jul 2019 Byungsoo Ko, Minchul Shin, Geonmo Gu, HeeJae Jun, Tae Kwan Lee, Youngjoon Kim

Many studies have been performed on metric learning, which has become a key ingredient in top-performing methods of instance-level image retrieval.

Image Retrieval Metric Learning +1

Combination of Multiple Global Descriptors for Image Retrieval

7 code implementations arXiv 2019 HeeJae Jun, Byungsoo Ko, Youngjoon Kim, Insik Kim, Jongtack Kim

Recent studies in image retrieval task have shown that ensembling different models and combining multiple global descriptors lead to performance improvement.

Image Retrieval Retrieval

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