Generative Adversarial Network has proven to produce state-of-the-art results by framing a generative modeling task into a supervised learning problem. In this paper, we propose Attentively Conditioned Generative Adversarial Network (ACGAN) for semantic segmentation by designing a segmentor model that generates probability maps from images and a discriminator model which discriminates the segmentor's output from the ground truth labels. Additionally, we conditioned the discriminator's dual inputs with extra information as a conditional adversarial model such that, an attention obtained probability distribution of the segmentor's feature maps is incorporated, and the ground truth is also accompanied by a vector of the class label. We demonstrate that our proposed model can provide better semantic segmentation results while stabilizing the discriminator to model long-range dependencies as a result of the supplementary inputs to the network. The attention network particularly provides more insights by extracting cues from the feature locations, and alongside the class label vector, gives the model an advantage to inform better spectral sensitivity. Experiments on the PASCAL VOC 2012 and the CamVid datasets show that our adversarial training technique yields improved accuracy. INDEX TERMS Generative adversarial network, deep convolutional neural network, attention network, conditional gan, semantic segmentation, deep learning.

No abstract

This paper lays emphasis on thedevelopment of low cost controllers for stepper motors in contrast to its resource limitations such as memory size, few I/O pins and computing power compared to High-end designs. The microchip AVR ATtiny45 microcontroller was employed alongside a redesigned (reduced-input pin count) pulse distribution circuit for two H-Bridge drivers. The motor can rotate in both directions as well as possible speed control. The concept of the motor control signals was modeled in Matlab/Simulink, firmware was written in Atmel AVRStudio development environment, while theoverall design was carried out in Proteus software followed by Hardware implementation. Total material cost is about $5 which would be less in commercial production cases.

No abstract

No abstract