1 code implementation • CVPR 2024 • Geonmo Gu, Sanghyuk Chun, Wonjae Kim, Yoohoon Kang, Sangdoo Yun
Our LinCIR (Language-only training for CIR) can be trained only with text datasets by a novel self-supervision named self-masking projection (SMP).
1 code implementation • 4 Dec 2023 • Geonmo Gu, Sanghyuk Chun, Wonjae Kim, Yoohoon Kang, Sangdoo Yun
Our LinCIR (Language-only training for CIR) can be trained only with text datasets by a novel self-supervision named self-masking projection (SMP).
1 code implementation • 21 Mar 2023 • Geonmo Gu, Sanghyuk Chun, Wonjae Kim, HeeJae Jun, Yoohoon Kang, Sangdoo Yun
This paper proposes a novel diffusion-based model, CompoDiff, for solving zero-shot Composed Image Retrieval (ZS-CIR) with latent diffusion.
no code implementations • 8 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.
no code implementations • 5 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.
1 code implementation • 28 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.
1 code implementation • 16 Dec 2021 • Young Kyun Jang, Geonmo Gu, Byungsoo Ko, Isaac Kang, Nam Ik Cho
To mitigate this issue, data augmentation can be applied during training.
2 code implementations • 1 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).
Ranked #6 on
Line Segment Detection
on York Urban Dataset
2 code implementations • 7 Apr 2021 • Minchul Shin, Yoonjae Cho, Byungsoo Ko, Geonmo Gu
In this paper, we study the compositional learning of images and texts for image retrieval.
Ranked #16 on
Image Retrieval
on Fashion IQ
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.
2 code implementations • 29 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.
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.
1 code implementation • 31 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.
1 code implementation • 17 Jan 2020 • Jungkyu Lee, Taeryun Won, Tae Kwan Lee, Hyemin Lee, Geonmo Gu, Kiho Hong
Recent studies in image classification have demonstrated a variety of techniques for improving the performance of Convolutional Neural Networks (CNNs).
Ranked #1 on
Fine-Grained Image Classification
on SOP
Fine-Grained Image Classification
Fine-Grained Visual Recognition
+4
no code implementations • 27 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.
no code implementations • 10 Dec 2017 • Wissam J. Baddar, Geonmo Gu, Sangmin Lee, Yong Man Ro
The spatial constructs of a generated video sequence are acquired from the target image.
no code implementations • 28 Nov 2017 • Geonmo Gu, Seong Tae Kim, Kihyun Kim, Wissam J. Baddar, Yong Man Ro
through a generative model is helpful in addressing the lack of training data.