no code implementations • 12 May 2021 • Wen Zhou, Seohyun Kim, Vijayaraghavan Murali, Gareth Ari Aye
Software language models have achieved promising results predicting code completion usages, and several industry studies have described successful IDE integrations.
no code implementations • NeurIPS 2020 • Seohyun Kim, Jaeyoo Park, Bohyung Han
We propose a local-to-global representation learning algorithm for 3D point cloud data, which is appropriate to handle various geometric transformations, especially rotation, without explicit data augmentation with respect to the transformations.
1 code implementation • 30 Mar 2020 • Seohyun Kim, Jinman Zhao, Yuchi Tian, Satish Chandra
We provide comprehensive experimental evaluation of our proposal, along with alternative design choices, on a standard Python dataset, as well as on a Python corpus internal to Facebook.
Ranked #1 on Type prediction on Py150
Type prediction Value prediction Software Engineering
no code implementations • 30 Jan 2020 • Jaedong Hwang, Seohyun Kim, Jeany Son, Bohyung Han
We present a weakly supervised instance segmentation algorithm based on deep community learning with multiple tasks.
Image-level Supervised Instance Segmentation object-detection +4
2 code implementations • 9 May 2019 • Jose Cambronero, Hongyu Li, Seohyun Kim, Koushik Sen, Satish Chandra
Our evaluation shows that: 1. adding supervision to an existing unsupervised technique can improve performance, though not necessarily by much; 2. simple networks for supervision can be more effective that more sophisticated sequence-based networks for code search; 3. while it is common to use docstrings to carry out supervision, there is a sizeable gap between the effectiveness of docstrings and a more query-appropriate supervision corpus.