| Title | Adaptively Weighted Channel Feature Network of Mixed Convolution Kernel |
| Publication Type | Conference Paper |
| Year of Publication | 2019 |
| Authors | Yuan, Yaofeng, When, JieChang |
| Conference Name | 2019 15th International Conference on Computational Intelligence and Security (CIS) |
| Date Published | dec |
| Keywords | adaptive weighting, adaptive weightings, attention mechanism, CIFAR10 dataset, CIFAR100 dataset, classification test, composability, compositionality, Computational Intelligence, convolutional neural nets, convolutional neural network, cryptography, deep learning networks, feature extraction, Heterojunction bipolar transistors, image classification, learning (artificial intelligence), machine-to-machine communications, mixed convolution kernel, multi channel grouping convolution, pubcrawl, security, sigmoid operator, weighted channel feature network |
| Abstract | In the deep learning tasks, we can design different network models to address different tasks (classification, detection, segmentation). But traditional deep learning networks simply increase the depth and breadth of the network. This leads to a higher complexity of the model. We propose Adaptively Weighted Channel Feature Network of Mixed Convolution Kernel(SKENet). SKENet extract features from different kernels, then mixed those features by elementwise, lastly do sigmoid operator on channel features to get adaptive weightings. We did a simple classification test on the CIFAR10 amd CIFAR100 dataset. The results show that SKENet can achieve a better result in a shorter time. After that, we did an object detection experiment on the VOC dataset. The experimental results show that SKENet is far ahead of the SKNet[20] in terms of speed and accuracy. |
| DOI | 10.1109/CIS.2019.00027 |
| Citation Key | yuan_adaptively_2019 |
Adaptively Weighted Channel Feature Network of Mixed Convolution Kernel