Chan Kha Vu

A curious human being

About

I’m a software engineer at Microsoft in Seattle Area, currently working on relevance ranking models at Bing Image Search. My opinion is that high quality data and good pipeline engineering is as important as fancy State-of-the-Art models. I feel lucky to be part of such a dynamic team at Bing!

Previously, I was a computer vision engineer at Samsung Research in Ukraine. I worked on projects related to monocular 3D reconstruction and optimizing Neural Networks for resource-constrained Mobile Devices.

On a side for fun, I travel to new places, blog about stuffs, paint, read (a lot of) Manga, play Go (feel free to send me a challenge), and a bit of Kaggling.

Timeline

2019 — Now
Microsoft, Seattle Area, USA
Software Engineer at Bing Image Search
2017 — 2019
Samsung Research, Ukraine
Research Computer Vision/AI Engineer
2017 — 2019
Taras Shevchenko National University
Master's degree in Applied Mathematics.
2013 — 2017
Taras Shevchenko National University
Bachelor's degree in Applied Mathematics

Blog Posts

Misc

My 9th place (solo gold) solution (out of 642 teams) for Kaggle’s Image Matching Challenge 2022 (by Google Research, part of CVPR’22 conference).

My 22nd Place Solution (out of 736 teams) for Google Landmarks Challenge 2020. I used EffNetB6, GemPool, and ArcMargin with dynamic margin scheduling.

hav4ik/Hydra — a Multi-Task Learning Framework on PyTorch. State-of-the-art methods are implemented to effectively train models on multiple tasks.

hav4ik/eyesight — A python framework for designing high-performance Computer Vision pipelines at the Edge. Supports Coral Edge TPU & Raspberry Pi Camera.