15 citations · 45 across the 7 of their papers we have counts for
11 papers · 1 filter
Group Generalized Mean Pooling for Vision Transformer
Byungsoo Ko, Han-Gyu Kim, Byeongho Heo +4
Vision Transformer (ViT) extracts the final representation from either class token or an average of all patch tokens, following the architecture of Transformer in Natural Language…
Granularity-aware Adaptation for Image Retrieval over Multiple Tasks
Jon Almazán, Byungsoo Ko, Geonmo Gu +2
Strong image search models can be learned for a specific domain, ie. set of labels, provided that some labeled images of that domain are available. A practical visual search model,…
Large-scale Bilingual Language-Image Contrastive Learning
Byungsoo Ko, Geonmo Gu
This paper is a technical report to share our experience and findings building a Korean and English bilingual multimodal model. While many of the multimodal datasets focus on Engli…
RTIC: Residual Learning for Text and Image Composition using Graph Convolutional Network
Minchul Shin, Yoonjae Cho, Byungsoo Ko +1
In this paper, we study the compositional learning of images and texts for image retrieval. The query is given in the form of an image and text that describes the desired modificat…
Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learning
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.…
Learning with Memory-based Virtual Classes for Deep Metric Learning
Byungsoo Ko, Geonmo Gu, Han-Gyu Kim
The core of deep metric learning (DML) involves learning visual similarities in high-dimensional embedding space. One of the main challenges is to generalize from seen classes of t…