AdaStereo: An Efficient Domain-Adaptive Stereo Matching Approach

Recently, records on stereo matching benchmarks are constantly broken by end-to-end disparity networks. However, the domain adaptation ability of these deep models is quite limited. Addressing such problem, we present a novel domain-adaptive approach called AdaStereo that aims to align multi-level representations for deep stereo matching networks. Compared to previous methods, our AdaStereo realizes a more standard, complete and effective domain adaptation pipeline. Firstly, we propose a non-adversarial progressive color transfer algorithm for input image-level alignment. Secondly, we design an efficient parameter-free cost normalization layer for internal feature-level alignment. Lastly, a highly related auxiliary task, self-supervised occlusion-aware reconstruction is presented to narrow the gaps in output space. We perform intensive ablation studies and break-down comparisons to validate the effectiveness of each proposed module. With no extra inference overhead and only a slight increase in training complexity, our AdaStereo models achieve state-of-the-art cross-domain performance on multiple benchmarks, including KITTI, Middlebury, ETH3D and DrivingStereo, even outperforming some state-of-the-art disparity networks finetuned with target-domain ground-truths. Moreover, based on two additional evaluation metrics, the superiority of our domain-adaptive stereo matching pipeline is further uncovered from more perspectives. Finally, we demonstrate that our method is robust to various domain adaptation settings, and can be easily integrated into quick adaptation application scenarios and real-world deployments.

Cross-Domain Topic Classification for Political Texts

We introduce and assess the use of supervised learning in cross-domain topic classification. In this approach, an algorithm learns to classify topics in a labeled source corpus and then extrapolates topics in an unlabeled target corpus from another domain. The ability to use existing training data makes this method significantly more efficient than within-domain supervised learning. It also has three advantages over unsupervised topic models: the method can be more specifically targeted to a research question and the resulting topics are easier to validate and interpret. We demonstrate the method using the case of labeled party platforms (source corpus) and unlabeled parliamentary speeches (target corpus). In addition to the standard within-domain error metrics, we further validate the cross-domain performance by labeling a subset of target-corpus documents. We find that the classifier accurately assigns topics in the parliamentary speeches, although accuracy varies substantially by topic. We also propose tools diagnosing cross-domain classification. To illustrate the usefulness of the method, we present two case studies on how electoral rules and the gender of parliamentarians influence the choice of speech topics.

Comparative Analysis of Selection Hyper-Heuristics for Real-World Multi-Objective Optimization Problems

As exact algorithms are unfeasible to solve real optimization problems, due to their computational complexity, meta-heuristics are usually used to solve them. However, choosing a meta-heuristic to solve a particular optimization problem is a non-trivial task, and often requires a time-consuming trial and error process. Hyper-heuristics, which are heuristics to choose heuristics, have been proposed as a means to both simplify and improve algorithm selection or configuration for optimization problems. This paper novel presents a novel cross-domain evaluation for multi-objective optimization: we investigate how four state-of-the-art online hyper-heuristics with different characteristics perform in order to find solutions for eighteen real-world multi-objective optimization problems. These hyper-heuristics were designed in previous studies and tackle the algorithm selection problem from different perspectives: Election-Based, based on Reinforcement Learning and based on a mathematical function. All studied hyper-heuristics control a set of five Multi-Objective Evolutionary Algorithms (MOEAs) as Low-Level (meta-)Heuristics (LLHs) while finding solutions for the optimization problem. To our knowledge, this work is the first to deal conjointly with the following issues: (i) selection of meta-heuristics instead of simple operators (ii) focus on multi-objective optimization problems, (iii) experiments on real world problems and not just function benchmarks. In our experiments, we computed, for each algorithm execution, Hypervolume and IGD+ and compared the results considering the Kruskal–Wallis statistical test. Furthermore, we ranked all the tested algorithms considering three different Friedman Rankings to summarize the cross-domain analysis. Our results showed that hyper-heuristics have a better cross-domain performance than single meta-heuristics, which makes them excellent candidates for solving new multi-objective optimization problems.

Connecting Images through Sources: Exploring Low-Data, Heterogeneous Instance Retrieval

Along with a new volume of images containing valuable information about our past, the digitization of historical territorial imagery has brought the challenge of understanding and interconnecting collections with unique or rare representation characteristics, and sparse metadata. Content-based image retrieval offers a promising solution in this context, by building links in the data without relying on human supervision. However, while the latest propositions in deep learning have shown impressive results in applications linked to feature learning, they often rely on the hypothesis that there exists a training dataset matching the use case. Increasing generalization and robustness to variations remains an open challenge, poorly understood in the context of real-world applications. Introducing the alegoria benchmark, containing multi-date vertical and oblique aerial digitized photography mixed with more modern street-level pictures, we formulate the problem of low-data, heterogeneous image retrieval, and propose associated evaluation setups and measures. We propose a review of ideas and methods to tackle this problem, extensively compare state-of-the-art descriptors and propose a new multi-descriptor diffusion method to exploit their comparative strengths. Our experiments highlight the benefits of combining descriptors and the compromise between absolute and cross-domain performance.

Metode Pieces Framework Pada Tingkat Kepuasan Pengguna Sistem Informasi Perpustakaan Universitas Muhammadiyah Sorong

Abstrak: Sistem informasi mempunyai peran penting dalam menghasilkan informasi bagi semua tingkatan manajemen. Analis perlu mengetahui keperluan informasi yang diinginkan manajemen agar informasi yang dihasilkan oleh sistem informasi dapat berfungsi dan tepat bagi manajemen. Proses evaluasi terhadap kinerja dari sistem informasi diperlukan untuk mengetahui apakah sistem informasi Universitas Muhammadiyah Sorong berjalan sebagaimana mestinya. Evaluasi sistem informasi dapat dilakukan dengan cara yang berbeda dan pada tingkatan yang berbeda, tergantung pada tujuan evaluasinya. Dalam melakukan kegiatan analisis dan evaluasi sistem informasi, terdapat beberapa metode atau model analisis yang dapat digunakan salah satunya adalah model analisis PIECES Framework. Untuk mempermudah evaluasi, ditawarkan cara analisis dengan kerangka PIECES Framework yang menguraikan ke dalam 6 fokus analisis kelemahan yaitu Performance, Information and Data, Economy, Control and Security, Eficiency dan Service. Tujuan penelitan ini untuk mengukur tingkat kepuasan, mengetahui kelemahan serta kekuatan dan menganalisis komponen-komponen yang diperlukan untuk meningkatkan kualitas pelayanan, yang terdapat pada sistem informasi perpustakaan Universitas Muhammadiyah Sorong. Berdasarkan hasil perhitungan daftar pernyataan yang diberikan kepada responden yang merupakan pengguna sistem informasi perpustakaan Universitas Muhammadiyah Sorong, domain Performance, Information & Data, Economics, Control & Security, Efficiency, dan Service, semua berada pada kategori puas, artinya penerapan sistem informasi perpustakaan Universitas Muhammadiyah Sorong, yang saat ini digunakan dilingkungan Kampus sudah dapat diterima sesuai dengan kerangka PIECES Framework. Kata kunci: kepuasan pengguna, PIECES Framework, website. Abstract: Information systems have an important role in producing information for all levels of management. Analysts need to know necessity of the information that management wants so that the information generated by the information system can function and be appropriate for management. The process of evaluating performance of the information system is needed to determine whether the information system at the University of Muhammadiyah Sorong is running as it should. Information systems evaluation can be carried out in different ways and at different levels, depending on objective of the evaluation. In carrying out information system analysis and evaluation activities, there are several methods or analysis models that can be used, one of which is the PIECES Framework analysis model. To simplify the evaluation, an analysis method is offered with the PIECES Framework which describes the 6 focus of weakness analysis, that are Performance, Information and Data, Economy, Control and Security, Efficiency and Service. The purpose of this research is to measure the level of satisfaction, find out the strengths, weaknesses and analyze the components that need to be improved the quality of service, which is contained in the library information system of the Muhammadiyah University of Sorong. Based on the results of the calculation of the list of statements given to respondents who are users of the library information system at the Muhammadiyah University of Sorong, the domain of Performance, Information & Data, Economics, Control & Security, Efficiency and Service, all of in the satisfied category, meaning that the application of the library information system at the Muhammadiyah University of Sorong , which is currently being used in the campus environment is acceptable in accordance with the PIECES Framework. Keywords: user satisfaction, PIECES Framework, website.

Evaluasi Penggunaan Supporting Applications For Quick Data Search (SuApQuDaS) Dengan Metode PIECES Framework

Aplikasi SuApQuDaS dibangun untuk memenuhi kebutuhan tim di salah satu biro dalam mengelola data khususnya proses pencarian data untuk meningkatkan pelayanan kepada customer. Evaluasi merupakan kegiatan terencana untuk menilai suatu permasalahan yang terjadi dengan menggunakan instrumen dan hasilnya dapat dibandingkan dengan tolak ukur untuk memperoleh kesimpulan sehingga ditemukan solusi untuk menyelesaikan permasalahan yang timbul. Sedangkan Evaluasi sistem informasi dapat dilakukan dengan cara yang berbeda dan pada tingkatan yang berbeda, tergantung pada tujuan evaluasinya. Tujuannya adalah untuk menilai kemampuan teknis, pelaksanaan operasional, dan pendayagunaan sistem. Untuk mempermudah evaluasi, ditawarkan cara analisis dengan kerangka PIECES yang menguraikan ke dalam 6 fokus analisis kelemahan yaitu Performance, Information and Data, Economy, Control and Security, Eficiency dan Service. Berdasarkan metode analisis kerangka kerja PIECES dalam mengukur tingkat evaluasi didapatkan nilai dari masing- masing domain yaitu domain performance memperoleh skor 4,09, domain information and data memperoleh skor 4,18, domain economics memperoleh skor 4,18, domain control and security memperoleh skor 4,11, domain efficiency memperoleh skor 4,17, dan domain service memperoleh skor 4,13.

Design of SWB Antenna with Triple Band Notch Characteristics for Multipurpose Wireless Applications

A compact concentric structured monopole antenna for super wide band (SWB) applications with triple notch band characteristics is designed and experimentally validated. The antenna covers an immense impedance bandwidth (1.6–47.5 GHz) with sharp triple notch bands at 1.8–2.2 GHz, 4–7.2 GHz, and 9.8–10.4 GHz to eliminate interference from co-existing advanced wireless services (AWS), C bands, and X bands, respectively. By loading an E-shaped stub connected at the top of the patch and by etching a split elliptical slot at the lower end of the radiating patch, the band rejection characteristics from 1.8–2.2 GHz for the AWS and 4–7.2 GHz for the C band are achieved, respectively. Further, by making use of a C-shaped resonator near the feed line, band rejection from 9.8–10.4 GHz for the X band is obtained. By varying the parameters of the antenna, the notch bands are controlled independently over a wide range of frequencies. The antenna provides good radiation characteristics, constant group delay response, and better gain over the pass band. The experimental results indicate that the designed antenna offers a remarkable reduction in gain and high variation in group delay over the stop bands. To characterize the wideband property and linear phase response of the designed antenna, its time-domain performance is extensively described and evaluated, which assure pulse transmission with minimum distortion.