BIOENGINEER

Hybrid Deep Learning Framework Enhances Blood Smear Platelet Detection and Counting

A hybrid deep learning framework combining lightweight super-resolution, transformer-based masked attention, and density ...

Cut out even a single strand of hair without SAM! Tencent's 'WeVisOne-VL' is too interesting, integrating 7 roles including detection, OCR, and transparency into one

"I want to ask the AI to look at an image and say 'circle the red mug,' 'extract only the text,' and 'remove the background ...
GitHub

Meta Research

The balance python package offers a simple workflow and methods for dealing with biased data samples when looking to infer from them to some target population of interest.

SAM不要で髪の毛1本まで切り抜く！検出・OCR・透過の7役を1つに統合したTencent『WeVisOne-VL』が面白すぎる

「AIに画像を見せて『赤いマグカップを囲んで』『文字だけ抜き出して』『人物の髪の毛まで綺麗に背景透過して』と頼みたいのに、用途ごとに別々のAIモデルを繋ぎ合わせるのが大変すぎる……」 ...