Digital Library[ Search Result ]
Neural Network Learning Method using Weight Mirroring and Direct Feedback Error
Soha Lee, Heesung Yang, Hyeyoung Park
http://doi.org/10.5626/JOK.2024.51.5.445
Error backpropagation algorithm is a core learning algorithm of neural networks and, until recently, has been used in various deep learning models. However, the weight update rule of error backpropagation, in which the error signal of the upper layer is sequentially transmitted to the lower layer and the weight values of the upper layer that are used to update the lower layer weights, has a problem of biological implausibility and computational inefficiency. To address these issues, learning methods using separate backward weights have been proposed, but they are still at an early stage and require further analysis and improvement from various perspectives. In this paper, we proposed a new learning method by combining the direct feedback alignment method, which directly projects the errors of the last layer into each hidden layer, and a weight mirror method with a separate step for updating backward weights. The proposed method overcomes the limitations of learning methods to implement a weight update method that is biologically plausible and allows for more efficient parallel learning. We confirmed the potential of the proposed method through experiments on various benchmark datasets.
Object Recognition in Low Resolution Images using a Convolutional Neural Network and an Image Enhancement Network
Injae Choi, Jeongin Seo, Hyeyoung Park
http://doi.org/10.5626/JOK.2018.45.8.831
Recently, the development of deep learning technologies such as convolutional neural networks have greatly improved the performance of object recognition in images. However, object recognition still has many challenges due to large variations in images and the diversity of object categories to be recognized. In particular, studies on object recognition in low-resolution images are still in the primary stage and have not shown satisfactory performance. In this paper, we propose an image enhancement neural network to improve object recognition performance of low resolution images. We also use the enhanced images for training an object recognition model based on convolutional neural networks to obtain robust recognition performance with resolution changes. To verify the efficiency of the proposed method, we conducted computational experiments on object recognition in a low-resolution environment using the CIFAR-10 and CIFAR-100 databases. We confirmed that the proposed method can greatly improve the recognition performance in low-resolution images while keeping stable performance in the original resolution images.
Detection of Faces with Partial Occlusions using Statistical Face Model
Face detection refers to the process extracting facial regions in an input image, which can improve speed and accuracy of recognition or authorization system, and has diverse applicability. Since conventional works have tried to detect faces based on the whole shape of faces, its detection performance can be degraded by occlusion made with accessories or parts of body. In this paper we propose a method combining local feature descriptors and probability modeling in order to detect partially occluded face effectively. In training stage, we represent an image as a set of local feature descriptors and estimate a statistical model for normal faces. When the test image is given, we find a region that is most similar to face using our face model constructed in training stage. According to experimental results with benchmark data set, we confirmed the effect of proposed method on detecting partially occluded face.
Search
Journal of KIISE
- ISSN : 2383-630X(Print)
- ISSN : 2383-6296(Electronic)
- KCI Accredited Journal
Editorial Office
- Tel. +82-2-588-9240
- Fax. +82-2-521-1352
- E-mail. chwoo@kiise.or.kr