22 citations · 51 across the 9 of their papers we have counts for
9 papers
Representation and decomposition of functions in DAG-DNNs and structural network pruning
Wen-Liang Hwang
The conclusions provided by deep neural networks (DNNs) must be carefully scrutinized to determine whether they are universal or architecture dependent. The term DAG-DNN refers to…
Deriving RIP sensing matrices for sparsifying dictionaries
Jinn Ho, Wen-Liang Hwang
Compressive sensing involves the inversion of a mapping , where , is a sensing matrix, and is a sparisfying dictionary. The restricte…
Analysis of function approximation and stability of general DNNs in directed acyclic graphs using un-rectifying analysis
Wen-Liang Hwang, Shih-Shuo Tung
A general lack of understanding pertaining to deep feedforward neural networks (DNNs) can be attributed partly to a lack of tools with which to analyze the composition of non-linea…
CDGNet: Class Distribution Guided Network for Human Parsing
Kunliang Liu, Ouk Choi, Jianming Wang +1
The objective of human parsing is to partition a human in an image into constituent parts. This task involves labeling each pixel of the human image according to the classes. Since…
FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation
Jaemin Na, Heechul Jung, Hyung Jin Chang +1
Unsupervised domain adaptation (UDA) methods for learning domain invariant representations have achieved remarkable progress. However, most of the studies were based on direct adap…
Densely Guided Knowledge Distillation using Multiple Teacher Assistants
Wonchul Son, Jaemin Na, Junyong Choi +1
With the success of deep neural networks, knowledge distillation which guides the learning of a small student network from a large teacher network is being actively studied for mod…
Pacemaker: Intermediate Teacher Knowledge Distillation For On-The-Fly Convolutional Neural Network
Wonchul Son, Youngbin Kim, Wonseok Song +2
There is a need for an on-the-fly computational process with very low performance system such as system-on-chip (SoC) and embedded device etc. This paper presents pacemaker knowled…
Residual Convolutional Neural Network Revisited with Active Weighted Mapping
Jung HyoungHo, Lee Ryong, Lee Sanghwan +1
In visual recognition, the key to the performance improvement of ResNet is the success in establishing the stack of deep sequential convolutional layers using identical mapping by…
Sequential Image-based Attention Network for Inferring Force Estimation without Haptic Sensor
Hochul Shin, Hyeon Cho, Dongyi Kim +3
Humans can infer approximate interaction force between objects from only vision information because we already have learned it through experiences. Based on this idea, we propose a…