204 citations · 294 across the 6 of their papers we have counts for
6 papers
On the Role of ViT and CNN in Semantic Communications: Analysis and Prototype Validation
Hanju Yoo, Linglong Dai, Songkuk Kim +1
Semantic communications have shown promising advancements by optimizing source and channel coding jointly. However, the dynamics of these systems remain understudied, limiting rese…
Curved Representation Space of Vision Transformers
Juyeop Kim, Junha Park, Songkuk Kim +1
Neural networks with self-attention (a.k.a. Transformers) like ViT and Swin have emerged as a better alternative to traditional convolutional neural networks (CNNs). However, our u…
Demo: Real-Time Semantic Communications with a Vision Transformer
Hanju Yoo, Taehun Jung, Linglong Dai +2
Semantic communications are expected to enable the more effective delivery of meaning rather than a precise transfer of symbols. In this paper, we propose an end-to-end deep neural…
How Do Vision Transformers Work?
Namuk Park, Songkuk Kim
The success of multi-head self-attentions (MSAs) for computer vision is now indisputable. However, little is known about how MSAs work. We present fundamental explanations to help…
Vector Quantized Bayesian Neural Network Inference for Data Streams
Namuk Park, Taekyu Lee, Songkuk Kim
Bayesian neural networks (BNN) can estimate the uncertainty in predictions, as opposed to non-Bayesian neural networks (NNs). However, BNNs have been far less widely used than non-…
Measuring the Eccentricity of Items
Chanyoung Park, Songkuk Kim
The long-tail phenomenon tells us that there are many items in the tail. However, not all tail items are the same. Each item acquires different kinds of users. Some items are loved…