Search

In this paper, we introduce an end-to-end generative adversarial network (GAN) based on sparse learning for single image blind motion deblurring, which we called SL-CycleGAN. For the first time in blind motion deblurring, we propose a sparse ResNet-block as a combination of sparse convolution layers and a trainable spatial pooler k-winner based on HTM (Hierarchical Temporal Memory) to replace non-linearity such as ReLU in the ResNet-block of SL-CycleGAN generators. Furthermore, unlike many state-of-the-art GAN-based motion deblurring methods that treat motion deblurring as a linear end-to-end process, we take our inspiration from the domain-to-domain translation ability of CycleGAN, and we show that image deblurring can be cycle-consistent while achieving the best qualitative results. Finally, we perform extensive experiments on popular image benchmarks both qualitatively and quantitatively and achieve the record-breaking PSNR of 38.087 dB on GoPro dataset, which is 5.377 dB better than the most recent deblurring method., Comment: 12 pages

This paper presents a novel context-aware image denoising algorithm that combines an adaptive image smoothing technique and color reduction techniques to remove perturbation from adversarial images. Adaptive image smoothing is achieved using auto-threshold canny edge detection to produce an accurate edge map used to produce a blurred image that preserves more edge features. The proposed algorithm then uses color reduction techniques to reconstruct the image using only a few representative colors. Through this technique, the algorithm can reduce the effects of adversarial perturbations on images. We also discuss experimental data on classification accuracy. Our results showed that the proposed approach reduces adversarial perturbation in adversarial attacks and increases the robustness of the deep convolutional neural network models., Comment: 5 pages, 3 figures, 1 table

Post-secondary education institutions in Taiwan are divided into two tracks, general higher education (HE) and technological and vocational education (TVE). The evaluation of all universities/colleges is mandated by the University Act. Higher education institutions receive mandated institutional evaluation every six years and program evaluation every five years. The purpose of this paper is to briefly introduce the status of higher education institutional and program evaluations in Taiwan as well as the emerging roles of the Higher Education Evaluation and Accreditation Council of Taiwan (HEEACT). Both institutional and program evaluations are accreditation-oriented, adopting the PDCA (Plan-Do-Check-Act) cycle with an emphasis on institutional and program self-positioning, student learning outcome, and mechanism for continuous improvement. As the third-party planner and implementer of higher education institutional and program evaluations, HEEACT has conducted internal and external assessments as well as entrusted third-party meta-evaluation to assure its quality of work. Faced with the emerging challenges, such as the Ministry of Education's new policy on requiring some universities/colleges to implement self-conducted external evaluation in replacement of the third-party program evaluation, HEEACT has to alter its roles and becomes a Critical Friend of higher education institutions and programs, a Change Agent of higher education institutional and program evaluation, and an Effective Facilitator of the international exchanges and cooperation on quality assurance and mutual recognitions of national qualifications. (Contains 3 figures.)