Sketch recognition remains a significant challenge due to the limited training data and substantial intra-class variance of freehand sketches for same object. Conventional methods this task often rely on availability temporal order sketch strokes, additional cues acquired from different modalities supervised augmentation datasets with real images, which also limit applicability feasibility thes...

Behavioral Cloning (BC) is a simple and effective imitation learning algorithm, which suffers from compounding error due to covariate shift. One solution use enough data for training. However, the amount of expert demonstrations available usually limited. So we propose an method augment alleviate problem in BC. It operates by estimating similarity states filtering out transitions that can go ba...

Data augmentation, the artificial creation of training data for machine learning by transformations, is a widely studied research field across disciplines. While it useful increasing model's generalization capabilities, can also address many other challenges and problems, from overcoming limited amount to regularizing objective, limiting used protect privacy. Based on precise description goals ...

background: several grafting materials have been used for alveolar ridge augmentation. the literature lacks researches to compare cenobone to other grafting materials. the aim of this study was to compare cenobone/cenomembrane complex to bio-oss/bio-gide complex in lateral alveolar bone augmentation in terms of radiographic, histologic, and histomorphometric parameters. materials and methods: i...

Data augmentation is an important technique to improve data efficiency and save labeling cost for 3D detection in point clouds. Yet, existing policies have so far been designed only utilize labeled data, which limits the diversity. In this paper, we recognize that pseudo are complementary, thus propose leverage unlabeled enrich training data. particular, design three novel pseudo-label based (P...

Abstract NLP has achieved great progress in the past decade through use of neural models and large labeled datasets. The dependence on abundant data prevents from being applied to low-resource settings or novel tasks where significant time, money, expertise is required label massive amounts textual data. Recently, augmentation methods have been explored as a means improving efficiency NLP. To d...