The easiest way to skyrocket your YouTube subscribers
Get Free YouTube Subscribers, Views and Likes

Segment Anything Model (SAM) from Meta AI: model architecture data engine results and limitations

Follow
AI Bites

Meta AI recently introduce a foundational model for image segmentation called Segment Anything Model or SAM in short. This video explain the motivation for SAM, the model architecture, its novel SA1B dataset and the results and limitations of zeroshot transfer learning.

Hope its useful.

segment anything website: https://segmentanything.com
segment anything code: https://github.com/facebookresearch/s...
segment anything demo: https://segmentanything.com/demo
SA1B dataset:   / segmentanythingdownloads  


⌚ ⌚ ⌚ TIMESTAMPS ⌚ ⌚ ⌚
0:00 Foundational models in NLP
1:07 Problem with Vision Models
2:01 Prompting in Segmentation
2: 56 SAM Model Architecture
5:15 SAM Model Animation
6:15 SAM Model Training (Data Engine)
9:21 SA1B Dataset
10:04 ZeroShot Transfer Learning Tasks
11:33 ZeroShot Transfer Learning Results


TOYS OF THE TRADE

XPPen for my scribbles https://amzn.to/3HNOpPH
⌨ My Keyboard & Mouse https://amzn.to/3XKZ3wF
My Monitor https://amzn.to/3YdVpvT
My GPUs https://amzn.to/3YE2aXX
My Mic https://amzn.to/3YCdDHA
My work desk https://amzn.to/3GWF1IP

MY SOFTWARE TOOLS
✍ Notion https://affiliate.notion.so/aibitesyt
✍ Notion AI https://affiliate.notion.so/ys9rqzv2vdd8
OBS Studio for video editing https://obsproject.com
Manim for some animations https://www.manim.community

BOOKS I HAVE READ, REFER AND RECOMMEND
Deep Learning by Ian Goodfellow https://amzn.to/3Wnyixv
Pattern Recognition and Machine Learning by Christopher M. Bishop https://amzn.to/3ZVnQQA
Machine Learning: A Probabilistic Perspective by Kevin Murphy https://amzn.to/3kAqThb
Multiple View Geometry in Computer Vision by R Hartley and A Zisserman https://amzn.to/3XKVOWi

MY KEY LINKS
YouTube:    / @aibites  
Twitter:   / ai_bites​  
Patreon:   / ai_bites​  
Github: https://github.com/aibites​

WHO AM I?
I am a Machine Learning Researcher / Practioner who has seen the grind of academia and startups equally. I started my career as a software engineer 15 years back. Because of my love for Mathematics (coupled with a glimmer of luck), I graduated with a Master's in Computer Vision and Robotics in 2016 when the now happening AI revolution just started. Life has changed for the better ever since.

#machinelearning #deeplearning #aibites

posted by chiliesx5