Search Results for author:
Found 13 papers, 3 papers with code
Instance Segmentation under Occlusions via Location-aware Copy-Paste Data Augmentation
Given the modest size of the dataset and the highly deformable nature of the objects to be segmented, this challenge demands the application of robust data augmentation techniques and wisely-chosen deep learning architectures.
Fairness-enhancing mixed effects deep learning improves fairness on in- and out-of-distribution clustered (non-iid) data
MEDL separately quantifies cluster-invariant fixed effects (FE) and cluster-specific random effects (RE) through the introduction of: 1) a cluster adversary which encourages the learning of cluster-invariant FE, 2) a Bayesian neural network which quantifies the RE, and a mixing function combining the FE an RE into a mixed-effect prediction.
ARIST: An Effective API Argument Recommendation Approach
To implement this idea in the recommendation process, ARIST combines program analysis (PA), language models (LMs), and several features specialized for the recommendation task which consider the functionality of formal parameters and the positional information of code elements (e. g., variables or method calls) in the given context.
TLETA: Deep Transfer Learning and Integrated Cellular Knowledge for Estimated Time of Arrival Prediction
Importantly, our transfer models only train the last layers to map the transferred knowledge, that reduces the training time significantly.
Reducing Catastrophic Forgetting in Neural Networks via Gaussian Mixture Approximation
Our paper studies the continual learning (CL) problems in which data comes in sequence and the trained models are expected to be capable of utilizing existing knowledge to solve new tasks without losing performance on previous ones.
IoT Data Discovery: Routing Table and Summarization Techniques
Specifically, as the first in the field, this paper investigates routing table designs and various compression techniques to support effective and space-efficient IoT data discovery routing.
Three-Way Deep Neural Network for Radio Frequency Map Generation and Source Localization
In this paper, we present a Generative Adversarial Network (GAN) machine learning model to interpolate irregularly distributed measurements across the spatial domain to construct a smooth radio frequency map (RFMap) and then perform localization using a deep neural network.
Into Summarization Techniques for IoT Data Discovery Routing
Also, our approach outperforms DHT based approaches by 2 to 6 folds in terms of latency and traffic.
Price Discrimination in the Presence of Customer Loyalty and Differing Firm Costs
We study how loyalty behavior of customers and differing costs to produce undifferentiated products by firms can influence market outcomes.
Structured Dropout Variational Inference for Bayesian Neural Networks
Approximate inference in Bayesian deep networks exhibits a dilemma of how to yield high fidelity posterior approximations while maintaining computational efficiency and scalability.
Improving Relational Regularized Autoencoders with Spherical Sliced Fused Gromov Wasserstein
To improve the discrepancy and consequently the relational regularization, we propose a new relational discrepancy, named spherical sliced fused Gromov Wasserstein (SSFG), that can find an important area of projections characterized by a von Mises-Fisher distribution.
Does BLEU Score Work for Code Migration?
In this paper, we conducted an empirical study on BLEU score to (in)validate its suitability for the code migration task due to its inability to reflect the semantics of source code.
Recovering Variable Names for Minified Code with Usage Contexts
JSNeat follows a data-driven approach to recover names by searching for them in a large corpus of open-source JS code.
