Adversarial training is an effective way to defend deep neural networks (DNN) against adversarial examples. However, there are atypical samples that rare and hard learn, or even hurt DNNs' generalization performance on test data. In this paper, we propose a novel algorithm reweight the based self-supervised techniques mitigate negative effects of samples. Specifically, memory bank built record ...

Ship instance segmentation in synthetic aperture radar (SAR) images can provide more detailed location information and shape information, which is of great significance for port ship scheduling traffic management. However, there little research work on SAR segmentation, the general accuracy low because characteristics target task, such as multi-scale, aspect ratio, noise interference, are not c...

In remote sensing, it is often challenging to acquire or collect a large data set that accurately labeled. This difficulty usually due several issues, including but not limited the study site’s spatial area and accessibility, errors in global positioning system (GPS), mixed pixels caused by an image’s resolution. We propose approach, with two variations, estimates multiple-target signatures fro...

In this paper we propose a new algorithm, named NICE, to generate counterfactual explanations for tabular data that specifically takes into account algorithmic requirements often emerge in real-life deployments: (1) the ability provide an explanation all predictions, (2) being able handle any classification model (also non-differentiable ones), (3) efficient run time, and (4) providing multiple...

The Internet has led to the development of on-line markets, and computer scientists have designed various auction algorithms, as well as automated exchanges for standardized commodities; however, they have done little work on exchanges for complex nonstandard goods. We present an exchange system for trading complex goods, such as used cars or nonstandard financial securities. The system allows ...

This research provides the first support for a possible psychological universal: Human beings around the world derive emotional benefits from using their financial resources to help others (prosocial spending). In Study 1, survey data from 136 countries were examined and showed that prosocial spending is associated with greater happiness around the world, in poor and rich countries alike. To te...

in this article, we tried to identify mechanisms of technology transfer and their legal basis in buy-back contracts. then, analyze the effect of wto regulations on those contracts. in addition, answer these questions: what are legal mechanisms of technology transfer in buy-back contracts? what are the effects of acceptance of wto rules on technology transfer policies in buy-back contracts and t...

Internet auctions on eBay and Yahoo allow sellers to list their auctions with a “buy-now” option. In such auctions the seller sets a buy price at which a bidder may purchase the item immediately and end the auction. In the eBay version of a buy-now auction, the buy-now option disappears as soon as a bid is placed, while in the Yahoo version of the auction the buy-now option remains in effect th...

developing countries that have almost oil reserves have no enough mega projects' management ability, technology and finance resources to manage and finish a mega project. host countries for achievement these technologies and resources have to cooperate with foreign and international companies.  different contractual frameworks are used in conjunction with obtaining these technologies and c...