115 citations · 285 across the 10 of their papers we have counts for
12 papers
AnyFlow: Arbitrary Scale Optical Flow with Implicit Neural Representation
Hyunyoung Jung, Zhuo Hui, Lei Luo +5
To apply optical flow in practice, it is often necessary to resize the input to smaller dimensions in order to reduce computational costs. However, downsizing inputs makes the esti…
NIPQ: Noise proxy-based Integrated Pseudo-Quantization
Juncheol Shin, Junhyuk So, Sein Park +3
Straight-through estimator (STE), which enables the gradient flow over the non-differentiable function via approximation, has been favored in studies related to quantization-aware…
On the Overlooked Significance of Underutilized Contextual Features in Recent News Recommendation Models
Sungmin Cho, Hongjun Lim, Keunchan Park +2
Personalized news recommendation aims to provide attractive articles for readers by predicting their likelihood of clicking on a certain article. To accurately predict this probabi…
Fine-grained Semantics-aware Representation Enhancement for Self-supervised Monocular Depth Estimation
Hyunyoung Jung, Eunhyeok Park, Sungjoo Yoo
Self-supervised monocular depth estimation has been widely studied, owing to its practical importance and recent promising improvements. However, most works suffer from limited sup…
Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing
Hyunsu Kim, Yunjey Choi, Junho Kim +2
Generative adversarial networks (GANs) synthesize realistic images from random latent vectors. Although manipulating the latent vectors controls the synthesized outputs, editing re…
MEANTIME: Mixture of Attention Mechanisms with Multi-temporal Embeddings for Sequential Recommendation
Sung Min Cho, Eunhyeok Park, Sungjoo Yoo
Recently, self-attention based models have achieved state-of-the-art performance in sequential recommendation task. Following the custom from language processing, most of these mod…
PROFIT: A Novel Training Method for sub-4-bit MobileNet Models
Eunhyeok Park, Sungjoo Yoo
4-bit and lower precision mobile models are required due to the ever-increasing demand for better energy efficiency in mobile devices. In this work, we report that the activation i…
Tag2Pix: Line Art Colorization Using Text Tag With SECat and Changing Loss
Hyunsu Kim, Ho Young Jhoo, Eunhyeok Park +1
Line art colorization is expensive and challenging to automate. A GAN approach is proposed, called Tag2Pix, of line art colorization which takes as input a grayscale line art and c…
Precision Highway for Ultra Low-Precision Quantization
Eunhyeok Park, Dongyoung Kim, Sungjoo Yoo +1
Neural network quantization has an inherent problem called accumulated quantization error, which is the key obstacle towards ultra-low precision, e.g., 2- or 3-bit precision. To re…
Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implications
Jongsoo Park, Maxim Naumov, Protonu Basu +25
The application of deep learning techniques resulted in remarkable improvement of machine learning models. In this paper provides detailed characterizations of deep learning models…
Value-aware Quantization for Training and Inference of Neural Networks
Eunhyeok Park, Sungjoo Yoo, Peter Vajda
We propose a novel value-aware quantization which applies aggressively reduced precision to the majority of data while separately handling a small amount of large data in high prec…
Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications
Yong-Deok Kim, Eunhyeok Park, Sungjoo Yoo +3
Although the latest high-end smartphone has powerful CPU and GPU, running deeper convolutional neural networks (CNNs) for complex tasks such as ImageNet classification on mobile de…