The Jaccard loss, commonly referred to as the intersection-over-union loss, is commonly employed in the evaluation of segmentation quality due to its better perceptual quality and scale invariance, which lends appropriate relevance to small objects compared with per-pixel losses. We present a method for direct optimization of the per-image intersection-over-union loss in neural networks, in the...

In today’s digital society, electronic information is increasingly shared among different entities, and decisions are made based on common attributes. To address associated privacy concerns, the research community has begun to develop cryptographic techniques for controlled (privacy-preserving) information sharing. One interesting open problem involves two mutually distrustful parties that need...

Enterprise Grid enables sharing and aggregation of a set of computing or storage resources connected by enterprise network, but the availability of the resources in this environment varies widely. Thus accurate prediction of the availability of these resources can significantly improve the performance of executing compute-intensive complex scientific and business applications in enterprise Grid...

In this paper we present a hybrid approach based on combining fuzzy clustering, seed region growing, and Jaccard similarity coefficient algorithms to measure gray (GM) and white matter tissue (WM) volumes from magnetic resonance images (MRIs). The proposed algorithm incorporates intensity and anatomic information for segmenting of MRIs into different tissue classes, especially GM and WM. It sta...

We study the problem of domain search where a domain is a set of distinct values from an unspecified universe. We use Jaccard set containment score, defined as |Q ∩X|/|Q|, as the measure of relevance of a domain X to a query domain Q. Our choice of Jaccard set containment over Jaccard similarity as a measure of relevance makes our work particularly suitable for searching Open Data and data on t...

We present a document alignment method based on expanded lexical translation sets and document-level Jaccard similarity. We compare our approach to state-of-the-art methods on a variety of alignment tasks, showing that it outperforms alternative methods in most scenarios for both parallel and comparable corpora. The proposed method is highly portable, requiring only minimal seed information and...

Recent research on vector representation of words in texts bring new methods of evaluating distributional thesauri. One of such methods is the task of analogy queries. We evaluated the Sketch Engine thesaurus on a subset of analogy queries using several similarity options. We show that Jaccard similarity is better than the cosine one for bigger corpora, it even substantially outperforms the wor...

Multiple sclerosis (MS) is a chronic inflammatory demyelinating disease of the central nervous system manifested morphologically by inflammation, demyelination, axonal loss and gliosis. The Magnetic Resonance (MR) imaging, which presents high resolution and good differentiation between brain tissues, is considered the gold standard for the detection and evolution assessment of MS lesions. Fairl...

In this paper we describe our strategy in the course of our participation in the 2012 QA4MRE main task. We follow a lexical approach, based on both Word Proximity and similarity measures. In the former, we implement a method that was successfully applied in the “Who Wants to be a Millionaire” contest; in the later we use the notion of “extent”, that is, a passage that includes terms of the give...