arXiv subjects

Bin Kang

Publications and source records attributed to Bin Kang.

21 records · Page 2Linked to original sources

arXiv2020

BiCANet: Bi-directional Contextual Aggregating Network for Image Semantic Segmentation

Exploring contextual information in convolution neural networks (CNNs) has gained substantial attention in recent years for semantic segmentation. This paper introduces a Bi-directional Contextual Aggregating Network, called BiCANet, for semantic segmentation. Unlike previous approaches that encode context in feature space, BiCANet aggregates contextual cues from a categorical perspective, which is mainly consist of three parts: contextual condensed projection block (CCPB), bi-directional context interaction block (BCIB), and muti-scale contextual fusion block (MCFB). More specifically, CCPB learns a category-based mapping through a split-transform-merge architecture, which condenses contextual cues with different receptive fields from intermediate layer. BCIB, on the other hand, employs dense skipped-connections to enhance the class-level context exchanging. Finally, MCFB integrates multi-scale contextual cues by investigating short- and long-ranged spatial dependencies. To evaluate BiCANet, we have conducted extensive experiments on three semantic segmentation datasets: PASCAL VOC 2012, Cityscapes, and ADE20K. The experimental results demonstrate that BiCANet outperforms recent state-of-the-art networks without any postprocess techniques. Particularly, BiCANet achieves the mIoU score of 86.7%, 82.4% and 38.66% on PASCAL VOC 2012, Cityscapes and ADE20K testset, respectively.

cs.CV↗

arXiv2019

FDDWNet: A Lightweight Convolutional Neural Network for Real-time Sementic Segmentation

This paper introduces a lightweight convolutional neural network, called FDDWNet, for real-time accurate semantic segmentation. In contrast to recent advances of lightweight networks that prefer to utilize shallow structure, FDDWNet makes an effort to design more deeper network architecture, while maintains faster inference speed and higher segmentation accuracy. Our network uses factorized dilated depth-wise separable convolutions (FDDWC) to learn feature representations from different scale receptive fields with fewer model parameters. Additionally, FDDWNet has multiple branches of skipped connections to gather context cues from intermediate convolution layers. The experiments show that FDDWNet only has 0.8M model size, while achieves 60 FPS running speed on a single RTX 2080Ti GPU with a 1024x512 input image. The comprehensive experiments demonstrate that our model achieves state-of-the-art results in terms of available speed and accuracy trade-off on CityScapes and CamVid datasets.

cs.CV↗

arXiv2019

Transient microscopy for measuring heat transfer in single cells

Heat transfer and dissipation exists in almost any physical, chemical or biological systems. Cells, as the basic unit of life, undergo continuous heat transfer and dissipation during their metabolism. The heat transfer and dissipation within cells related to not only fundamental cellular functions and biochemical reactions, but also several important applications including heat-induced control of biological processes and treatment of diseases. Unfortunately, thus far, we still know very little about the heat transfer and dissipation properties at cellular or subcellular level. Here, we demonstrated a methodology of transient microscopy to map the heat transfer coefficients in single cells, with a temporal resolution of ~5 us and a spatial resolution of ~250 nm (close to diffraction limit). The heat transfer coefficients of different location within single cells were obtained for the first time, the inner part of cells exhibited nonuniform heat transfer properties, and it suggested a self-consistent heat transfer regulation that responds to environmental temperature.

physics.bio-ph↗