The paper proposes a solution based on Generative Adversarial Network (GAN) for solving jigsaw puzzles. The problem assumes that an image is divided into equal square pieces, and asks to recover the ...image according to information provided by the pieces. Conventional jigsaw puzzle solvers often determine the relationships based on the boundaries of pieces, which ignore the important semantic information. In this paper, we propose JigsawGAN, a GAN-based auxiliary learning method for solving jigsaw puzzles with unpaired images (with no prior knowledge of the initial images). We design a multi-task pipeline that includes, (1) a classification branch to classify jigsaw permutations, and (2) a GAN branch to recover features to images in correct orders. The classification branch is constrained by the pseudo-labels generated according to the shuffled pieces. The GAN branch concentrates on the image semantic information, where the generator produces the natural images to fool the discriminator, while the discriminator distinguishes whether a given image belongs to the synthesized or the real target domain. These two branches are connected by a flow-based warp module that is applied to warp features to correct the order according to the classification results. The proposed method can solve jigsaw puzzles more efficiently by utilizing both semantic information and boundary information simultaneously. Qualitative and quantitative comparisons against several representative jigsaw puzzle solvers demonstrate the superiority of our method.
This research aims to address issues occurring in the teaching process in class II of SD N Wirogunan 03 Kartasura, where mathematics instruction still follows a conventional model involving only ...teacher-led delivery without any real activities to aid students' understanding of the material. The proposed solution is to use puzzle-based learning media to enhance learning outcomes and student engagement in the learning process. This study employs the Classroom Action Research (CAR) method, comprising two cycles with a pre-cycle followed by planning, implementation, observation, and reflection stages. Evaluation of learning outcomes and student engagement is conducted using assessment sheets and observations. The research findings indicate that the use of puzzle-based learning media improves learning outcomes and student engagement. The percentage of learning outcomes in the pretest was 27.2%, increased to 54.6% in cycle I, and reached 81.9% in cycle II. Furthermore, student engagement in the pretest was 36.3%, increased to 63.7% in cycle I, and reached 100% in cycle II. From these research findings, it can be concluded that the use of puzzle-based media effectively enhances learning outcomes and student engagement, creating active and engaging learning experiences.
Books reviewed in this issue. The Monty Hall Problem: The Remarkable Story of Math's Most Contentious Brain Teaser Jason Rosenhouse What is a p-value Anyway? 34 Stories to Help You Actually ...Understand Statistics Andrew J. Vickers Surveying Natural Populations: Quantitative Tools for Assessing Biodiversity Lee-Ann C. Hayek and Martin A. Buzas PUBLICATION ABSTRACT