Related papers: Using Design Sketch to Teach Bubble Sort in High S…
Particle Dobble is an open-access, gamified learning tool designed to address persistent misconceptions in particle physics education by symbolically representing elements of the Standard Model. Aimed at upper secondary and introductory…
Deep Learning shows very good performance when trained on large labeled data sets. The problem of training a deep net on a few or one sample per class requires a different learning approach which can generalize to unseen classes using only…
Large-scale data is of crucial importance for learning semantic segmentation models, but annotating per-pixel masks is a tedious and inefficient procedure. We note that for the topic of interactive image segmentation, scribbles are very…
Random projections offer an appealing and flexible approach to a wide range of large-scale statistical problems. They are particularly useful in high-dimensional settings, where we have many covariates recorded for each observation. In…
Knowledge distillation (KD) aims to distill the knowledge from the teacher (larger) to the student (smaller) model via soft-label for the efficient neural network. In general, the performance of a model is determined by accuracy, which is…
Symbolic equations are one of the many representations used in physics. Understanding these representations is important for students because they are how students access knowledge in physics. In this paper I build off of the work by Redish…
Inspired by a common technique for shuffling a deck of cards on a table without riffling, we continue the study of a prequel paper on the pile shuffle and its capabilities as a sorting device. We study two sort feasibility problems of…
Background: Software modelling is a creative yet challenging task. Modellers often find themselves lost in the process, from understanding the modelling problem to solving it with proper modelling strategies and modelling tools. Students…
Designing multiscale visualizations, particularly when the ratio between the largest scale and the smallest item is large, can be challenging, and designers have developed many approaches to overcome this challenge. We present a design…
Knowledge distillation refers to the process of training a compact student network to achieve better accuracy by learning from a high capacity teacher network. Most of the existing knowledge distillation methods direct the student to follow…
In spite of great success in many image recognition tasks achieved by recent deep models, directly applying them to recognize low-resolution images may suffer from low accuracy due to the missing of informative details during resolution…
Knowledge distillation is widely used as a means of improving the performance of a relatively simple student model using the predictions from a complex teacher model. Several works have shown that distillation significantly boosts the…
One of the capabilities which 21st-century skill compulsory a person is critical thinking and problem-solving skill that becomes top positions rank. Focus on problem-solving skills can be taught to a child, especially begun in elementary…
We present a simple and efficient method based on deep learning to automatically decompose sketched objects into semantically valid parts. We train a deep neural network to transfer existing segmentations and labelings from 3D models to…
Sketching is one of the most fundamental tools in large-scale machine learning. It enables runtime and memory saving via randomly compressing the original large problem into lower dimensions. In this paper, we propose a novel sketching…
Visualizations support rapid analysis of scientific datasets, allowing viewers to glean aggregate information (e.g., the mean) within split-seconds. While prior research has explored this ability in conventional charts, it is unclear if…
Sketch as an image search query is an ideal alternative to text in capturing the fine-grained visual details. Prior successes on fine-grained sketch-based image retrieval (FG-SBIR) have demonstrated the importance of tackling the unique…
In this paper, we tackle for the first time, the problem of self-supervised representation learning for free-hand sketches. This importantly addresses a common problem faced by the sketch community -- that annotated supervisory data are…
In accordance with Bloom's taxonomy, a four-level evaluation abstraction was generated with the objective of structuring and hierarchizing curricula knowledge, allowing students to dominate a subject and progressively reach the top of…
Few-shot learning aims at leveraging knowledge learned by one or more deep learning models, in order to obtain good classification performance on new problems, where only a few labeled samples per class are available. Recent years have seen…