7 citations · 19 across the 7 of their papers we have counts for
6 papers · 1 filter
Analysis of NaN Divergence in Training Monocular Depth Estimation Model
Bum Jun Kim, Hyeonah Jang, Sang Woo Kim
The latest advances in deep learning have facilitated the development of highly accurate monocular depth estimation models. However, when training a monocular depth estimation netw…
Resolution-Aware Design of Atrous Rates for Semantic Segmentation Networks
Bum Jun Kim, Hyeyeon Choi, Hyeonah Jang +1
DeepLab is a widely used deep neural network for semantic segmentation, whose success is attributed to its parallel architecture called atrous spatial pyramid pooling (ASPP). ASPP…
Understanding Gaussian Attention Bias of Vision Transformers Using Effective Receptive Fields
Bum Jun Kim, Hyeyeon Choi, Hyeonah Jang +1
Vision transformers (ViTs) that model an image as a sequence of partitioned patches have shown notable performance in diverse vision tasks. Because partitioning patches eliminates…
Guidelines for the Regularization of Gammas in Batch Normalization for Deep Residual Networks
Bum Jun Kim, Hyeyeon Choi, Hyeonah Jang +3
L2 regularization for weights in neural networks is widely used as a standard training trick. However, L2 regularization for gamma, a trainable parameter of batch normalization, re…
Improved Robustness of Vision Transformer via PreLayerNorm in Patch Embedding
Bum Jun Kim, Hyeyeon Choi, Hyeonah Jang +3
Vision transformers (ViTs) have recently demonstrated state-of-the-art performance in a variety of vision tasks, replacing convolutional neural networks (CNNs). Meanwhile, since Vi…
Dead Pixel Test Using Effective Receptive Field
Bum Jun Kim, Hyeyeon Choi, Hyeonah Jang +3
Deep neural networks have been used in various fields, but their internal behavior is not well known. In this study, we discuss two counterintuitive behaviors of convolutional neur…