"Dive into Deep Learning. (arXiv:2106.11342v4 [cs.LG] UPDATED)" — An open-source book on Deep Learning based on Jupyter Notebooks so that it contains interactive examples. Freely available and well-worth checking out.

Paper: http://arxiv.org/abs/2106.11342
Code: https://github.com/d2l-ai/d2l-en
Book: https://d2l.ai/

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Image of book cover for Dive in…

"Scaling Vision Transformers to 22 Billion Parameters. (arXiv:2302.05442v1 [cs.CV])" — A recipe for highly efficient and stable training of a 22B-parameter Vision Transformers (ViT) overtaking the previously known 4B parameter model.

Paper: http://arxiv.org/abs/2302.05442

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Dense prediction from frozen Vi…

Sometimes, reading #MachineLearning papers, I find my brain turning off — I read the words, but I don’t get the meaning. I have to then stop myself and go back and read each of the words individually to make sense of them …

This probably is a sign that I need to stop reading papers 😛 But does this happen to anybody else? I think I’ve started doing this for everything, even fiction, and that’s why I can’t read as much any longer …

"Rumor Classification through a Multimodal Fusion Framework and Ensemble Learning. (arXiv:2302.05289v1 [cs.CV])" — A set of advanced image features that are inspired from the field of image quality assessment, to assess message veracIty in social networks, which exploits all message features by exploring various machine learning models.

Paper: http://arxiv.org/abs/2302.05289

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
An overview of the proposed rum…

"Archaeological Sites Detection with a Human-AI Collaboration Workflow. (arXiv:2302.05286v1 [cs.CV])" — Using pre-trained semantic segmentation deep learning models to detect archaeological sites within the Mesopotamian floodplains environment.

Paper: http://arxiv.org/abs/2302.05286
Code: https://github.com/mister-magpie/tell_segmentation

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Investigation area. Orange dots…

"CEN-HDR: Computationally Efficient neural Network for real-time High Dynamic Range imaging. (arXiv:2302.05213v1 [cs.CV])" — A new computationally efficient neural network based on a light attention mechanism and sub-pixel convolution operations for real-time HDR imaging.

Paper: http://arxiv.org/abs/2302.05213
Code: https://github.com/steven-tel/CEN-HDR

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Qualitative comparison of the p…

"DOMINO: Domain-aware Loss for Deep Learning Calibration. (arXiv:2302.05142v1 [cs.CV])" — A domain-aware loss function to calibrate deep learning models so as to avoid the potential dangers of uncalibrated models in medical imaging.

Paper: http://arxiv.org/abs/2302.05142
Code: https://github.com/lab-smile/DOMINO

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Confusion matrices on testing s…

"Example-Based Sampling with Diffusion Models. (arXiv:2302.05116v1 [cs.GR])" — A generic way to produce 2-d point sets imitating existing samplers from observed point sets using a diffusion model which addresses the problem of convolutional layers by leveraging neighborhood information from an optimal transport matching to a uniform grid, that allows benefiting from fast convolutions on grids, and to support the example-based learning of non-uniform sampling patterns.

Paper: http://arxiv.org/abs/2302.05116

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Learning Rank-1 realizations us…

A total of 84 papers in the cs.CV category on arXiv.org today — 53 new, 31 updated.

Don’t really feel ready for Monday … but ah, well … on to the papers!

#AI #CV #NewPapers #DeepLearning #MachineLearning

After 2 whole days of sun, the rain came back.... And this beauty as well.
Now we were both soaked, waiting for the shower to end but she gave me all the time to take a few portraits.

#BirdsinLatin #ButeoButeo
#Birdphotography #Birds #Birdsofthefediverse
#BirdsofMastodon #Wildlife #Wildlifephotography #Nature

Some mushrooms, moss and lichen from the nearby Beaver forest. BeaverCam only had taken 9 photos so it is staying. #mosstodon #fungi

The images show two separate iterations of the same app — the first is a SwiftUI app for doing #StableDiffusion image generation using #CoreML. That took several weeks of work to create and it never really worked right — I could only do single selection of images, couldn’t drag and drop more than one image, and it took a fair amount of time to implement even trivial stuff.

The second is the same app implemented using AppKit. It took essentially one day (yesterday). Multiselection was built-in, drag and drop (for multiple items) was a couple of lines of code, and I implemented a bunch of other things I wanted to do fairly easily.

On top of that, the app feels faster, lighter, and more responsive than the SwiftUI version for the exact same task, using the exact same models.

SwiftUI has a long way to go still, if it will even ever get there …

#Coding #macOS #Swift #SwiftUIvsAppKit
Screenshot of an image generati…
Screenshot of an image generati…

Another D&D session podcast released - traveling through Wildspace.

Our podcasts have shifted to more "cinematic" replays with lots of background music and sound effects.

Hope you enjoy!

https://open.spotify.com/episode/0ZmwWu4LX5QmQyVuSLIoYZ

#dnd #podcast #spelljammer

Sportscaster: I hope you're all ready for Super Bowl Sunday.

Me: No, but I am ready for Superb Owl Sunday haha

Owl: We get one single holiday and it's just a big fucking joke to you people.

I only go to Legoland for the discount plastic surgery.
https://patreon.com/lowqualityfacts

This is a fascinating article on the increasing use of #subtitles, by Claudia Forsberg for ABC #Ballarat - the way that sound is designed for movies intended for cinema means that it doesn't play back optimally on mobile devices or streaming services - and this is one factor driving the adoption of #ClosedCaptioning or #Subtitles.

But, these #Subtitles are often inaccurate or mis-transcribed. They use #ASR technology - and this is another case for having good #voice #data #voicedata

https://www.abc.net.au/news/2023-02-12/subtitles-popular-among-general-population-change-tv-film/101956758

"When asked to draw a scientist, school-age kids in the United States are increasingly sketching women. That's the main conclusion of a new study that compiled information about 20,860 pictures drawn by students age 5 to 18 over 5 decades."

https://www.science.org/content/article/what-does-scientist-look-children-are-drawing-women-more-ever #science @psychology @sociology

Genius.
https://patreon.com/lowqualityfacts

Opera is going to use #ChatGPT to shorten articles — so that people have to read less and think even less —, Microsoft is building ChatGPT into their Office tools — again, less thinking —, we already have ChatGPT in search engines ..

So this is how the world ends — everybody growing stupider because we are too lazy to think for ourselves, and not with a bang?

I guess SkyNet did arrive but not in the way we thought … 😛

#TheAIRevolution #MisinformationEngine
Engadget article — Opera is add…

#silentsunday