122 citations · 180 across the 8 of their papers we have counts for
9 papers
Optimal Transport-based Identity Matching for Identity-invariant Facial Expression Recognition
Daeha Kim, Byung Cheol Song
Identity-invariant facial expression recognition (FER) has been one of the challenging computer vision tasks. Since conventional FER schemes do not explicitly address the inter-ide…
CFA: Coupled-hypersphere-based Feature Adaptation for Target-Oriented Anomaly Localization
Sungwook Lee, Seunghyun Lee, Byung Cheol Song
For a long time, anomaly localization has been widely used in industries. Previous studies focused on approximating the distribution of normal features without adaptation to a targ…
Ensemble Knowledge Guided Sub-network Search and Fine-tuning for Filter Pruning
Seunghyun Lee, Byung Cheol Song
Conventional NAS-based pruning algorithms aim to find the sub-network with the best validation performance. However, validation performance does not successfully represent test per…
Vision Transformer for Small-Size Datasets
Seung Hoon Lee, Seunghyun Lee, Byung Cheol Song
Recently, the Vision Transformer (ViT), which applied the transformer structure to the image classification task, has outperformed convolutional neural networks. However, the high…
Contextual Gradient Scaling for Few-Shot Learning
Sanghyuk Lee, Seunghyun Lee, Byung Cheol Song
Model-agnostic meta-learning (MAML) is a well-known optimization-based meta-learning algorithm that works well in various computer vision tasks, e.g., few-shot classification. MAML…
Interpretable Embedding Procedure Knowledge Transfer via Stacked Principal Component Analysis and Graph Neural Network
Seunghyun Lee, Byung Cheol Song
Knowledge distillation (KD) is one of the most useful techniques for light-weight neural networks. Although neural networks have a clear purpose of embedding datasets into the low-…
Metric-based Regularization and Temporal Ensemble for Multi-task Learning using Heterogeneous Unsupervised Tasks
Dae Ha Kim, Seung Hyun Lee, Byung Cheol Song
One of the ways to improve the performance of a target task is to learn the transfer of abundant knowledge of a pre-trained network. However, learning of the pre-trained network re…
Graph-based Knowledge Distillation by Multi-head Attention Network
Seunghyun Lee, Byung Cheol Song
Knowledge distillation (KD) is a technique to derive optimal performance from a small student network (SN) by distilling knowledge of a large teacher network (TN) and transferring…
Self-supervised Knowledge Distillation Using Singular Value Decomposition
Seung Hyun Lee, Dae Ha Kim, Byung Cheol Song
To solve deep neural network (DNN)'s huge training dataset and its high computation issue, so-called teacher-student (T-S) DNN which transfers the knowledge of T-DNN to S-DNN has b…