## Maximizing Cosine Similarity Between Spatial Features for Unsupervised Domain Adaptation in Semantic Segmentation

A segmentation network mainly consists of two parts, a feature extractor and a classificationhead . We propose a novel method that tackles the problem of unsupervised domainadaptation for semantic segmentation . Our method computes a cosine similarity matrix between thesource feature map and the target feature map .…

## Emerging Trends in Federated Learning From Model Fusion to Federated X Learning

Federated learning is a new learning paradigm that decouples data collection and model training via multi-party computation and model aggregation . As aflexible learning setting, federated learning has the potential to integrate with other learning frameworks . This survey reviews the state of the art, challenges, and future directions of learning algorithms .…

## Optimized Memoryless Fair Share HPC Resources Scheduling using Transparent Checkpoint Restart Preemption

Common resource management methods in supercomputing systems usually include hard divisions, capping, and quota allotment . Those methods involve bad supply-and-demand management rather than a free market playground that will eventually increase system utilization and productivity . In this work, we propose the newly Optimized Memoryless Fair-Share HPCResources Scheduling using Transparent Checkpoint-Restart Preemption, in which the social welfare increases using a free-of-cost interchangeable proprietarypossession scheme .…

## Investigating the Limitations of the Transformers with Simple Arithmetic Tasks

The ability to perform arithmetic tasks is a remarkable trait of human intelligence . In this work, we investigate if the surface form of a number has any influence on how sequence-to-sequence language models learn simple arithmetictasks such as addition and subtraction .…

## File fragment recognition based on content and statistical features

The known files are divided into different fragments, and different classificational algorithms are used to solve the problems of file fragment recognition . The proposed recognition algorithm can recognize 6 types of useful files and may distinguish a type of file fragments with higher accuracy thanthe similar works done .…

## Self Tuning for Data Efficient Deep Learning

Deep learning has made revolutionary advances to diverse applications in the presence of large-scale labeled datasets . However, it is prohibitively time-costly and labor-expensive to collect sufficient labeled data in most realistic scenarios . To mitigate the requirement for labeled data, SSL focuses on exploring both labeled and unlabeled data, while transfer learning popularizes a favorable practice of fine-tuning a pre-trained model to the target data .…

## Checkpointing and Localized Recovery for Nested Fork Join Programs

This extended abstract suggests to adapt a checkpointing and localized recovery technique that has originally been developed for independent tasks tonested fork-join programs . The original technique has checkpointing overheads below1% and neglectable costs for recovery, we expect the new algorithm to achieve asimilar performance .…

## Sentiment Analysis of Persian English Code mixed Texts

The rapid production of data on the internet and the need to understand howusers are feeling from a business and research perspective has prompted the need for an automatic monolingual sentiment detection systems . We then introduce a model which uses BERT pretrained embeddings as well as translation models to automaticallylearn the polarity scores of these Tweets .…

## On the Estimation of the Number of Unreachable Peers in the Bitcoin P2P Network by Observation of Peer Announcements

Bitcoin is based on a P2P network that is used to propagate transactions and blocks . While the number of reachable peers can be measured, it is inherently difficult to determine thenumber of unreachable peers . We propose the PAL (PassiveAnnouncement Listening) method to analyze data from along-term measurement of the Bitcoin network .…

## Fragmented Objects Boosting Concurrency of SharedLarge Objects

This work examines strategies to handle large shared data objects indistributed storage systems (DSS) While boosting the number of concurrentaccesses, maintaining strong consistency guarantees, and ensuring goodoperation performance, we define the notion of fragmentedobjects:con-current objects composed of a list of fragments (or blocks) As thefragments belong to the same object, it is not enough that each fragment is linearizable to have useful consistency guarantees in the composed object .…

## Persistent Homology and Graphs Representation Learning

This article aims to study the topological invariant properties encoded innode graph representational embeddings by utilizing tools available in persistent homology . Our construction effectivelydefines a unique persistence-based graph descriptor, on both the graph and nodelevels, for every node representation algorithm .…

## Real Time Ellipse Detection for Robotics Applications

We propose a new algorithm for real-time detection and tracking of ellipticpatterns suitable for real world robotics applications . The method fitssellipses to each contour in the image frame and rejects ellipses that do not yield a good fit . It can detect complete, partial, and imperfect ellipse inextreme weather and lighting conditions and is lightweight enough to be used on robots’ resource-limited onboard computers .…

## FERMI Fair Empirical Risk Minimization via Exponential Rényi Mutual Information

In this paper, we propose a new notion of fairness violation, calledExponential R\’enyi Mutual Information (ERMI) We show ERMI is a strongfairness violation notion in the sense that it provides upper bound guarantees on existing notions of fairness violation . We then propose the Fair EmpiricalRisk Minimization via ERMI regularization framework, called FERMI .…

## SCD A Stacked Carton Dataset for Detection and Segmentation

Carton detection is an important technique in the automatic logistics system . Images are collected from the internet and several warehourses, and objects are labeled using per-instancesegmentation for precise localization . There are totally 250,000 instance masksfrom 16,136 images . The improvement of AP on MS COCO and PASCAL VOC is 1.8% – 2.2% and 3.4% – 4.3% respectively.…

## Blockchained Federated Learning for Threat Defense

Security systems fail to detect serious threats such as zero-day attacks . The need for more active and more effective security methods keeps increasing . The proposed framework combinesFederated Learning for the distributed and continuously validated learning of the tracing algorithms .…

## Benchmarking and Survey of Explanation Methods for Black Box Models

The widespread adoption of black-box models in Artificial Intelligence has increased the need for explanation methods to reveal how these obscure models reach specific decisions . We provide acategorization of explanation methods based on the type of explanation returned . We present the most recent and widely used explainers, and we show avisual comparison among explanations and a quantitative benchmarking .…

## Machine Learning Based Optimal Mesh Generation in Computational Fluid Dynamics

Computational Fluid Dynamics (CFD) is a major sub-field of engineering . Finding an optimal mesh is key for computational efficiency . The proposed concept is validated along 2d wind tunnel simulations with more than 60,000 simulations . Corresponding predictions of optimal meshes can be used as input for any meshgeneration and CFD tool.…

## Generalized Parametric Path Problems

Parametric path problems arise independently in diverse domains, ranging from transportation to finance, where they are studied under various assumptions . We show that when the parametric weights are linear, algorithms remain tractable even under relaxed assumptions . If the weights are allowed to be non-linear, the problem becomes NP-hard.…

## Quantization Algorithms for Random Fourier Features

Method of random projection (RP) is the standard technique in machinelearning and many other areas, for dimensionality reduction, approximate nearneighbor search, compressed sensing, etc. The method of random Fourierfeatures (RFF) applies a specific nonlinear transformation on the projected data from random projections .…

## Where to go next Learning a Subgoal Recommendation Policy for Navigation Among Pedestrians

Robotic navigation in environments shared with other robots or humans remains challenging because the intentions of the surrounding agents are not directlyobservable . This paper proposes to learn, via deepReinforcement Learning (RL), an interaction-aware policy that provides long-term guidance to the local planner .…