10 citations · 15 across the 3 of their papers we have counts for
4 papers
Self-Taught Metric Learning without Labels
Sungyeon Kim, Dongwon Kim, Minsu Cho +1
We present a novel self-taught framework for unsupervised metric learning, which alternates between predicting class-equivalence relations between data through a moving average of…
ReSTR: Convolution-free Referring Image Segmentation Using Transformers
Namyup Kim, Dongwon Kim, Cuiling Lan +2
Referring image segmentation is an advanced semantic segmentation task where target is not a predefined class but is described in natural language. Most of existing methods for thi…
Embedding Transfer with Label Relaxation for Improved Metric Learning
Sungyeon Kim, Dongwon Kim, Minsu Cho +1
This paper presents a novel method for embedding transfer, a task of transferring knowledge of a learned embedding model to another. Our method exploits pairwise similarities betwe…
Proxy Anchor Loss for Deep Metric Learning
Sungyeon Kim, Dongwon Kim, Minsu Cho +1
Existing metric learning losses can be categorized into two classes: pair-based and proxy-based losses. The former class can leverage fine-grained semantic relations between data p…