4 papers
On Train-Test Class Overlap and Detection for Image Retrieval
Chull Hwan Song, Jooyoung Yoon, Taebaek Hwang +3
How important is it for training and evaluation sets to not have class overlap in image retrieval? We revisit Google Landmarks v2 clean, the most popular training set, by identifyi…
SyncMask: Synchronized Attentional Masking for Fashion-centric Vision-Language Pretraining
Chull Hwan Song, Taebaek Hwang, Jooyoung Yoon +2
Vision-language models (VLMs) have made significant strides in cross-modal understanding through large-scale paired datasets. However, in fashion domain, datasets often exhibit a d…
Conditional Cross Attention Network for Multi-Space Embedding without Entanglement in Only a SINGLE Network
Chull Hwan Song, Taebaek Hwang, Jooyoung Yoon +2
Many studies in vision tasks have aimed to create effective embedding spaces for single-label object prediction within an image. However, in reality, most objects possess multiple…
GRIT-VLP: Grouped Mini-batch Sampling for Efficient Vision and Language Pre-training
Jaeseok Byun, Taebaek Hwang, Jianlong Fu +1
Most of the currently existing vision and language pre-training (VLP) methods have mainly focused on how to extract and align vision and text features. In contrast to the mainstrea…