Maria Rodriguez

A surgeon, educator and researcher -- One learning machine!

[Maria Rodriguez @Maria_Rod_Data]

Drove in good road conditions this afternoon from Hamilton to Gananoque. Thank you to the traffic and clearing staff! #ON511

[Maria Rodriguez @Maria_Rod_Data]

Datathon for EarthDay, hosted by DataForGood-Vancouver on April 23-24! Register here: https://t.co/vSvk1PyVra

[Maria Rodriguez @Maria_Rod_Data]

https://t.co/cgxBoPfr9g @wandb #ArtificialIntelligence #surgery

[Maria Rodriguez @Maria_Rod_Data]

@robmarkcole LOL! Quite polite.

[Maria Rodriguez @Maria_Rod_Data]

Very organized datathon with a noble task of understanding the homelessness situation. Thank you @DataForGoodYYC, @calgaryhomeless and @RBC !

[Maria Rodriguez @Maria_Rod_Data]

@ishanjainn @ai_fast_track @fastdotai @SharpestMindsAI @ishanjainn I only used YOLOv5 for this one. It's a great idea to compare the different versions, though! :)

[Maria Rodriguez @Maria_Rod_Data]

Models also have their personalities. Some are meticulous. Some are funky rapid. Some are efficiency freaks. Meet them here: https://t.co/LYbo1wiiK8 @ai_fast_track @fastdotai @SharpestMindsAI #DeepLearning

[Robin Cole @robmarkcole]

YOLOX ready for action in Icevision 🥳🥶

[Farid @ai_fast_track]

🧐7 things you should know about the Focal Loss:

📌 It was introduced in the RetinaNet paper to address the foreground-background class imbalance encountered during training of dense detectors (one-stage detectors)
...

[Data for Good YVR @dataforgoodyvr]

Check out this great event #DataScience community. Nov 10: Meet the data scientist who's working on Amazon's Alexa: https://t.co/rbBxF4YzH1 #OpenData #DataViz

[Farid @ai_fast_track]

🥇YOLOX beat YOLOv5. They won the 1st Place on Streaming Perception Challenge (Workshop on Autonomous Driving at CVPR 2021).

I briefly explain how they created it, here below👇

YOLOX will be soon supported in our IceVision Framework (Repo: https://t.co/wNQen4X65M)

[Yann LeCun @ylecun]

A short history of neural net architectures 1958-2021.

[Maria Rodriguez @Maria_Rod_Data]

Uhm, no, that's not a Laptop, let's try again... 😆 #ComputerVision

[Maria Rodriguez @Maria_Rod_Data]

I want to label thousands of images myself... said no researcher ever 😅 https://t.co/4vFh3aaJPL @ai_fast_track @fastdotai @SharpestMindsAI @roboflowai #DeepLearning #ComputerVision #ArtificialIntelligence

[Maria Rodriguez @Maria_Rod_Data]

@jeremyphoward @CSIRO Congratulations! :)

[Maria Rodriguez @Maria_Rod_Data]

Uploading annotations in CVAT is quite a challenge. Anybody has a tip to share? #ArtificialIntelligence #annotation

[Maria Rodriguez @Maria_Rod_Data]

Awesome example of AI working for social good. https://t.co/sg1BYgYldQ @OrbisIntl #ArtificialIntelligence

[Farid @ai_fast_track]

#SmallObjectDetection
Here is another good technique to detect small objects when you have access to high resolution images. Inference is done on patches/slices and then stitched together.

Repo: https://t.co/FsMPHZzUFP

[Maria Rodriguez @Maria_Rod_Data]

AI is cool. Not just because it can recognize our face or recommend a movie that we actually like. But because it can help satisfy one of our basic human needs: Food. https://t.co/PyjJ3K2TOB @ai_fast_track @SharpestMindsAI @fastdotai #DeepLearning

[Maria Rodriguez @Maria_Rod_Data]

This paper by Rieke et al shows Federated Learning as one of the possible ways of bridging silos in medical data without compromising confidentiality. https://t.co/0u2Pd7BnTi #MachineLearning #DataScience #deeplearning #medicaldata

[Farid @ai_fast_track]

#SmallObjectDetection
Interesting approach for detecting tiny objects as small as 2 × 2 pixels. It uses Multi-Scale Semantic Segmentation. Anchor free.

Paper: Oriented Bounding Boxes for Small and Freely
Rotated Objects
pdf: https://t.co/H7H3cMKZm3
abs: https://t.co/Pu8s9TTo67