Related papers: Using Design Sketch to Teach Bubble Sort in High S…
Sketch colorization is a critical task for automating and assisting in the creation of animations and digital illustrations. Previous research identified the primary difficulty as the distribution shift between semantically aligned training…
This paper describes a hierarchical system that predicts one label at a time for automated student response analysis. For the task, we build a classification binary tree that delays more easily confused labels to later stages using…
Scatterplot selection is an effective approach to represent essential portions of multidimensional data in a limited display space. Various metrics for evaluation of scatterplots such as scagnostics have been presented and applied to…
In this paper I describe an in-class discussion activity aimed at helping elementary education majors in a physical science course think about issues surrounding the inclusion of "Intelligent Design" in public school science standards. I…
For linear systems $Ax=b$ we develop iterative algorithms based on a sketch-and-project approach. By using judicious choices for the sketch, such as the history of residuals, we develop weighting strategies that enable short recursive…
This paper is concerned with self-supervised learning for small models. The problem is motivated by our empirical studies that while the widely used contrastive self-supervised learning method has shown great progress on large model…
Following recent breakthroughs in convolutional neural networks and monolithic model architectures, state-of-the-art object detection models can reliably and accurately scale into the realm of up to thousands of classes. Things quickly…
Recent advances in self-supervised learning have experienced remarkable progress, especially for contrastive learning based methods, which regard each image as well as its augmentations as an individual class and try to distinguish them…
Few-shot image classification aims to classify unseen classes with limited labelled samples. Recent works benefit from the meta-learning process with episodic tasks and can fast adapt to class from training to testing. Due to the limited…
We study scalable and uniform understanding of facts in images. Existing visual recognition systems are typically modeled differently for each fact type such as objects, actions, and interactions. We propose a setting where all these facts…
Emphasizing problem formulation in AI literacy activities with children is vital, yet we lack empirical studies on their structure and affordances. We propose that participatory design involving teachable machines facilitates problem…
The promising performances of CNNs often overshadow the need to examine whether they are doing in the way we are actually interested. We show through experiments that even over-parameterized models would still solve a dataset by recklessly…
Natural language and images are commonly used as goal representations in goal-conditioned imitation learning (IL). However, natural language can be ambiguous and images can be over-specified. In this work, we propose hand-drawn sketches as…
We propose a novel clustering pipeline that combines two classic clustering algorithms to better understand student problem-solving strategies. This unsupervised machine learning method helps uncover patterns in reasoning without…
Knowledge distillation aims to compress a powerful yet cumbersome teacher model into a lightweight student model without much sacrifice of performance. For this purpose, various approaches have been proposed over the past few years,…
We introduce a new sub-linear space sketch---the Weight-Median Sketch---for learning compressed linear classifiers over data streams while supporting the efficient recovery of large-magnitude weights in the model. This enables…
Data reduction in storage systems is becoming increasingly important as an effective solution to minimize the management cost of a data center. To maximize data-reduction efficiency, existing post-deduplication delta-compression techniques…
Understanding how people perceive visualizations is crucial for designing effective visual data representations; however, many heuristic design guidelines are derived from specific tasks or visualization types, without considering the…
In this paper, we present Scratch Community Blocks, a new system that enables children to programmatically access, analyze, and visualize data about their participation in Scratch, an online community for learning computer programming. At…
Helping students become proficient problem-solvers is one of the primary goals of physics courses. In part 1 of this article, we summarized the vast research on problem-solving relevant for physics instruction, and here we discuss a…