Search Results for author: Audris Mockus

Found 9 papers, 3 papers with code

SLRNet: Semi-Supervised Semantic Segmentation Via Label Reuse for Human Decomposition Images

1 code implementation24 Feb 2022 Sara Mousavi, Zhenning Yang, Kelley Cross, Dawnie Steadman, Audris Mockus

We evaluate our method on a large dataset of human decomposition images and find that our method, while conceptually simple, outperforms state-of-the-art consistency and pseudo-labeling-based methods for the segmentation of this dataset.

Segmentation Semi-Supervised Semantic Segmentation

Pseudo Pixel-level Labeling for Images with Evolving Content

no code implementations20 May 2021 Sara Mousavi, Zhenning Yang, Kelley Cross, Dawnie Steadman, Audris Mockus

Annotating images for semantic segmentation requires intense manual labor and is a time-consuming and expensive task especially for domains with a scarcity of experts, such as Forensic Anthropology.

Pseudo Label Segmentation +1

Effect of Technical and Social Factors on Pull Request Quality for the NPM Ecosystem

no code implementations8 Jul 2020 Tapajit Dey, Audris Mockus

We proposed seven hypotheses regarding which technical and social factors might affect PR acceptance and created 17 measures based on them.

Software Engineering D.2.7

Representation of Developer Expertise in Open Source Software

no code implementations20 May 2020 Tapajit Dey, Andrey Karnauch, Audris Mockus

Aim: We aim to address this knowledge gap by proposing and constructing the Skill Space where each API, developer, and project is represented and postulate how the topology of this space should reflect what developers know (and projects need).

Collaborative Learning of Semi-Supervised Clustering and Classification for Labeling Uncurated Data

no code implementations9 Mar 2020 Sara Mousavi, Dylan Lee, Tatianna Griffin, Dawnie Steadman, Audris Mockus

In our experiment comparing manual labeling with labeling conducted with the support of Plud, we found that it reduces the time needed to label data and produces highly accurate models for this new domain.

Clustering General Classification

Detecting and Characterizing Bots that Commit Code

2 code implementations2 Mar 2020 Tapajit Dey, Sara Mousavi, Eduardo Ponce, Tanner Fry, Bogdan Vasilescu, Anna Filippova, Audris Mockus

Background: Some developer activity traditionally performed manually, such as making code commits, opening, managing, or closing issues is increasingly subject to automation in many OSS projects.

An Analytical Workflow for Clustering Forensic Images

no code implementations29 Dec 2019 Sara Mousavi, Dylan Lee, Tatianna Griffin, Dawnie Steadman, Audris Mockus

Large collections of images, if curated, drastically contribute to the quality of research in many domains.


Machine-assisted annotation of forensic imagery

no code implementations28 Feb 2019 Sara Mousavi, Ramin Nabati, Megan Kleeschulte, Audris Mockus

In the case of a large forensic collection, we are aiming to annotate, neither the complete annotation nor the large training samples can be feasibly produced.

Segmentation Transfer Learning

ALFAA: Active Learning Fingerprint Based Anti-Aliasing for Correcting Developer Identity Errors in Version Control Data

2 code implementations10 Jan 2019 Sadika Amreen, Audris Mockus, Chris Bogart, Yuxia Zhang, Russell Zaretzki

We also find supervised learning methods to reduce errors by several times in comparison to existing methods and the active learning approach to be an effective way to create validated datasets and that correction of developer identity has a large impact on the inference of the social network.

Software Engineering

Cannot find the paper you are looking for? You can Submit a new open access paper.