7 citations · 13 across the 3 of their papers we have counts for
6 papers
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.…
An Effective Pipeline for a Real-world Clothes Retrieval System
Yang-Ho Ji, HeeJae Jun, Insik Kim +7
In this paper, we propose an effective pipeline for clothes retrieval system which has sturdiness on large-scale real-world fashion data. Our proposed method consists of three comp…
Embedding Expansion: Augmentation in Embedding Space for Deep Metric Learning
Byungsoo Ko, Geonmo Gu
Learning the distance metric between pairs of samples has been studied for image retrieval and clustering. With the remarkable success of pair-based metric learning losses, recent…
Symmetrical Synthesis for Deep Metric Learning
Geonmo Gu, Byungsoo Ko
Deep metric learning aims to learn embeddings that contain semantic similarity information among data points. To learn better embeddings, methods to generate synthetic hard samples…
A Benchmark on Tricks for Large-scale Image Retrieval
Byungsoo Ko, Minchul Shin, Geonmo Gu +3
Many studies have been performed on metric learning, which has become a key ingredient in top-performing methods of instance-level image retrieval. Meanwhile, less attention has be…
Combination of Multiple Global Descriptors for Image Retrieval
HeeJae Jun, Byungsoo Ko, Youngjoon Kim +2
Recent studies in image retrieval task have shown that ensembling different models and combining multiple global descriptors lead to performance improvement. However, training diff…