PinnedKornia 0.6 — High Level Computer Vision for AIKornia is a modern set of Computer Vision libraries built on top of PyTorch that implements curated low level Computer Vision algorithms for the areas of robotics, camera localization and AR. To learn more about the library and our ecosystem visit our Documentation and dive into our interactive Tutorials to…Pytorch5 min readPytorch5 min read
Jan 6, 2021Life lessons learned from XCOM Impossible IronmanRecently I have twice beaten XCOM in the hardest mode — Impossible Ironman. It took me a lot of time to learn things, which helped me to beat the game. Ironically, most of the things I learned are not related to the game. Are you ready? Let’s go. In case…Games4 min readGames4 min read
Nov 19, 2020Should we apply high standards to those, who speak about high standards?Let’s speak about ethics. Recently we have submitted our position paper “ArXiving Before Submission Helps Everyone” to NeurIPS 2020 Workshop on “Navigating the Broader Impacts of AI Research” (NBIAIR). We had two motivations for the submission. 1. The main motivation was to continue the discussion, which started with our two…Artificial Intelligence4 min readArtificial Intelligence4 min read
Aug 21, 2020What does it mean to publish your scientific paper in 2020?Benefits to authors of non-anonymous preprints. Written by Dmytro Mishkin and Amy Tabb One of the most popular reactions to our previous post was: “we generally agree, so let’s allow preprints before acceptance, but in anonymous form only.” The current post addresses this idea, and to do it properly, we…Scientific Publishing9 min readScientific Publishing9 min read
Jun 29, 2020Hands off arXiv!Introduction Recently, we have seen renewed calls that conference submissions should not be posted on arXiv prior to acceptance. The main arguments of these calls are the following: Why can’t you wait 3–6 months? Double blind review becomes a single blind review, which reduces diversity and by some studies have shown…Arxiv6 min readArxiv6 min read
Jun 20, 2020Враження від віртуальної CVPR 2020По гарячих слідах після CVPR2020 збираю до купи думки про віртуальні наукові конференції. Чи дорівнює віртуальна конфа реальній, чи ні? Давайте розбиратися. CVPR складається з 3х складових — воркшопів, туторіалів та власне основної конференції. Основна конференція — це презентація наукових результатів (статей) у вигляді постерів та доповідей. Постер-сесія — це…Cvpr 20205 min readCvpr 20205 min read
Apr 18, 2020Собор чи базар штучного інтелекту?Кількість публікацій в галузі штучного інтелекту (ШІ) така, що ніхто не встигає пропрацювати всі. Чи не здається мені, що це якось неправильно? Ні, не здається. Поясню чому. Почну з того, що це — невідворотній процес у будь-якій галузі. Час енциклопедистів проходить, настає час все більш і більш вузьких спеціалістів. Давно…Machine Learning2 min readMachine Learning2 min read
Feb 19, 2020How we did technical interviews (spoiler: no whiteboard coding)I have been criticizing whiteboard interviews for a while. Now it is time to tell, how we approached them in our startup, Clear Research. First, setup. We were based in Kyiv, Ukraine, in 2014. There are lots of talented engineers there, but no university was teaching computer vision or machine…Interview4 min readInterview4 min read
Jun 20, 2019How to match: to learn or not to learn? (part 2)Let`s continue to study the nuances of image correspondences finding. Last time we have covered SIFT implementations. Now I`ll show you how to improve the matching part of the process for free (or almost for free). Recap: local features are detected and local image regions around them are embedded to…Machine Learning4 min readMachine Learning4 min read
Jun 4, 2019Machine learning research as a product. How easy is it to use your work?The best research is when you are answering questions that bother you and it happens to be in line with your company/grant proposal goals. …Machine Learning3 min readMachine Learning3 min read
