200 citations · 293 across the 5 of their papers we have counts for
5 papers
Unsupervised Model Drift Estimation with Batch Normalization Statistics for Dataset Shift Detection and Model Selection
Wonju Lee, Seok-Yong Byun, Jooeun Kim +2
While many real-world data streams imply that they change frequently in a nonstationary way, most of deep learning methods optimize neural networks on training data, and this leads…
Data Proxy Generation for Fast and Efficient Neural Architecture Search
Minje Park
Due to the recent advances on Neural Architecture Search (NAS), it gains popularity in designing best networks for specific tasks. Although it shows promising results on many bench…
JGAN: A Joint Formulation of GAN for Synthesizing Images and Labels
Minje Park
Image generation with explicit condition or label generally works better than unconditional methods. In modern GAN frameworks, both generator and discriminator are formulated to mo…
PVANet: Lightweight Deep Neural Networks for Real-time Object Detection
Sanghoon Hong, Byungseok Roh, Kye-Hyeon Kim +2
In object detection, reducing computational cost is as important as improving accuracy for most practical usages. This paper proposes a novel network structure, which is an order o…
PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection
Kye-Hyeon Kim, Sanghoon Hong, Byungseok Roh +2
This paper presents how we can achieve the state-of-the-art accuracy in multi-category object detection task while minimizing the computational cost by adapting and combining recen…