activity
20192022
most citedCSPNet: A New Backbone that can Enhance Learning Capability of CNN

361 citations · 395 across the 7 of their papers we have counts for

collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV20223 cited

SARAS-Net: Scale and Relation Aware Siamese Network for Change Detection

Chao-Peng Chen, Jun-Wei Hsieh, Ping-Yang Chen +2

Change detection (CD) aims to find the difference between two images at different times and outputs a change map to represent whether the region has changed or not. To achieve a be…

cs.CV2022

NAS-based Recursive Stage Partial Network (RSPNet) for Light-Weight Semantic Segmentation

Yi-Chun Wang, Jun-Wei Hsieh, Ming-Ching Chang

Current NAS-based semantic segmentation methods focus on accuracy improvements rather than light-weight design. In this paper, we proposed a two-stage framework to design our NAS-b…

cs.CV2022

Siamese-NAS: Using Trained Samples Efficiently to Find Lightweight Neural Architecture by Prior Knowledge

Yu-Ming Zhang, Jun-Wei Hsieh, Chun-Chieh Lee +1

In the past decade, many architectures of convolution neural networks were designed by handcraft, such as Vgg16, ResNet, DenseNet, etc. They all achieve state-of-the-art level on d…

cs.CV20221 cited

SFPN: Synthetic FPN for Object Detection

Yu-Ming Zhang, Jun-Wei Hsieh, Chun-Chieh Lee +1

FPN (Feature Pyramid Network) has become a basic component of most SoTA one stage object detectors. Many previous studies have repeatedly proved that FPN can caputre better multi-s…

cs.CV20215 cited

Learnable Discrete Wavelet Pooling (LDW-Pooling) For Convolutional Networks

Bor-Shiun Wang, Jun-Wei Hsieh, Ming-Ching Chang +3

Pooling is a simple but essential layer in modern deep CNN architectures for feature aggregation and extraction. Typical CNN design focuses on the conv layers and activation functi…

cs.CV202125 cited

CSL-YOLO: A New Lightweight Object Detection System for Edge Computing

Yu-Ming Zhang, Chun-Chieh Lee, Jun-Wei Hsieh +1

The development of lightweight object detectors is essential due to the limited computation resources. To reduce the computation cost, how to generate redundant features plays a si…