Geometrical and deep learning approaches for instance segmentation of CFRP fiber bundles in textile composites

Semantic Instance Segmentation via Deep Metric Learning

We propose a new method for semantic instance segmentation, by first computing how likely two pixels are to belong to the same object, and then by grouping similar pixels together. Our similarity metric is based on a deep, fully convolutional embedding model. Our grouping method is based on selecting all points that are sufficiently similar to a set of “seed points’, chosen from a deep, fully c...

Production of Banana Fiber Yarns for Technical Textile Reinforced Composites

Natural fibers have been used as an alternative to synthetic ones for their greener character; banana fibers have the advantage of coming from an agricultural residue. Fibers have been extracted by mechanical means from banana tree pseudostems, as a strategy to valorize banana crops residues. To increase the mechanical properties of the composite, technical textiles can be used as reinforcement...

Integrating Deep Learning and Multiple Instance Learning

assessment of deep word knowledge in elementary and advanced iranian efl learners: a comparison of selective and productive wat tasks

testing plays a vital role in any language teaching program. it allows teachers and stakeholders, including program administrators, parents, admissions officers and prospective employers to be assured that the learners are progressing according to an accepted standard (douglas, 2010). the problems currently facing language testers have both practical and theoretical implications but the first i...

Deep Learning for Single-View Instance Recognition

Deep learning methods have typically been trained on large datasets in which many training examples are available. However, many real-world product datasets have only a small number of images available for each product. We explore the use of deep learning methods for recognizing object instances when we have only a single training example per class. We show that feedforward neural networks outp...