In honor of Throwback Thursday, here's my first ever pumpkin vine showing off one of its first blossoms. We weren't even serious (at first) about growing pumpkins that year! I dropped three seeds into an unprepared spot and kind of toed some dirt over them. They all sprouted and we got several pumpkins. #Gardening #ThrowbackThursday

Smart.
https://patreon.com/lowqualityfacts

I saw a meme on tumblr earlier that said the best response to “Can you explain this gap in your resume” is “No I signed an NDA”

#LifeHack

White Daffodils And Daisies in a mixed media photography, painting and digital painting combination!

Add to your #homedecor and/or products for #spring here: https://sandi-oreilly.pixels.com/featured/white-daffodils-and-daisies-sandi-oreilly.html

See more #art here: https://sandi-oreilly.pixels.com/

Greatly Appreciate Follows and Boosts!!😊

I love #animals, #horses working with#blindhorses #nature #painting #photography #PhotoMonday #digitalart, #walking, #gardening . #AYearForArt #ArtMatters #MastoArt #fediart #FediGiftShop #humanartist

This male White Tailed Deer was feeding on the vegetation in #Guelph #Ontario #Canada and posed just long enough for me to capture the portrait. Whitetail Deer antlers begin growing in early spring and are fully grown by late summer.
Check it out here
https://debbie-oppermann.pixels.com/featured/white-tailed-buck-portrait-ii-debbie-oppermann.html
#WhiteTailedDeer #deer #animal #wildlife #mammal #WildlifePhotography #nature #AnimalLover #photography #buck #AnimalsOfMastodon #WildlifeWednesday #AYearForArt #ArtBooster #WhiteTail #artwork #AnimalPhotography

Hi #Astrodon now that I've migrated servers, it's #introduction time again!

I'm John Wu (he/him), a tenure-track Assistant Astronomer at the Space Telescope Science Institute! I study how galaxies grow and evolve by using deep learning and astronomical surveys--and occasionally multi-wavelength targeted observations too.

Happy to connect with others in the #astronomy, #science, #MachineLearning, #physics, and #math communities!

Hopper

2023-01-02-03/06 day 231/234 of doing art every day for a year (mostly - I took sick days off).

I am posting this piece out of order - I still have a backlog to catch up on. I'll get to that after this one.

No tutorial for this one. This is by request from Fahim. He had the idea of an egg-shaped rabbit sort of creature called a Hopper, not to be confused with Sri Lankan hoppers which are a food thing. https://en.wikipedia.org/wiki/Appam

I had some fur brushes I wanted to try out, so I did. And then it morphed into an alien landscape since, well, I felt like it plus it was to go along with a short story Fahim wrote that takes place in The Basement of the Universe, a place we created together, in our 50 Galaxies universe. Yep, there's a huge backstory here.

I've posted a link to Fahim's story and a time lapse of the digital painting on my blog, which you can find here: http://lmashton.com/hopper/

#ArtMatters #AYearForArt #Procreate #ProcreateArt #DigitalArt #WomensArt #WomenArtists #ArtistsOnMastodon
A white with purple undertones …

And that’s another run of papers done — 8 papers in the cs.CV category (and 2 outside) boosted out of the total of 71 new and updated papers released on arXiv.org today …

That’s enough papers for me for today 🙂

#AI #CV #NewPapers #DeepLearning #MachineLearning

"What do we learn? Debunking the Myth of Unsupervised Outlier Detection. (arXiv:2206.03698v2 [cs.CV] UPDATED)" — An investigation into what Auto-Encoders (AE) actually learn when they are posed to solve two different tasks and challenging the assumption that AEs are likely to be even better at reconstructing some types of Out-of-Distribution (OoD) samples.

Paper: http://arxiv.org/abs/2206.03698

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Unsupervised outlier detection …

"Improved Vector Quantized Diffusion Models. (arXiv:2205.16007v2 [cs.CV] UPDATED)" — Two techniques to improve the sample quality of VQ-Diffusion. 1) Explore classifier-free guidance sampling for discrete denoising diffusion models to propose a more general and effective implementation of classifier-free guidance. 2) Use a high-quality inference strategy to alleviate the joint distribution issue in VQ-Diffusion.

Paper: http://arxiv.org/abs/2205.16007
Code: https://github.com/microsoft/vq-diffusion
Demos: https://huggingface.co/spaces/patrickvonplaten/vq-vs-stable-diffusion
https://huggingface.co/spaces/williamberman/vq-diffusion

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
In-the-wild text-to-image synth…

this is one of my favorite pictures i've taken. it's hard to see when not zoomed in but above this little #PalmWarbler there's a grasshopper sitting on a leaf. i love a good bogo deal. #birds #grasshoppers #prairie

“Mining Effective Features Using Quantum Entropy for Humor Recognition” — A paper which looks at dividing a joke into two components — the setup and the punchline — and examining the possible semantics and relationships between these components.

Paper: https://arxiv.org/abs/2302.03716

#NewPaper #Language #Computation

<<Find this useful? Please boost so that others can benefit too 🙂>>
A humor and non-humor example c…

"STILL AROUND": Experiences and Survival Strategies of Veteran Women Software Developers
— 14 interviews to examine the experiences of people at the intersection of ageism and sexism to see how these factors can create a hostile environment for veteran software developers belonging to marginalized genders.

Paper: https://arxiv.org/abs/2302.03723

#NewPaper #SoftwareEngineering

<<Find this useful? Please boost so that others can benefit too 🙂>>

Sitting with a warm, furry, relaxed puppy on your lap is the absolute best way to wait for the sun to set.
For your viewing pleasure, here is the sunset on the beautiful north coast of California. Almost in real time.
Mastodon was a great find for me when I needed an outlet most.
Sending feel-good vibes your way.
#Sunset

"Zero-shot Generation of Coherent Storybook from Plain Text Story using Diffusion Models. (arXiv:2302.03900v1 [cs.CV])" — A neural pipeline for generating a coherent storybook from the plain text of a story by leveraging a combination of a pre-trained Large Language Model and a text-guided Latent Diffusion Model to generate coherent images.

Paper: http://arxiv.org/abs/2302.03900

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Zero-shot generation example of…

"Neural Artistic Style Transfer with Conditional Adversaria. (arXiv:2302.03875v1 [cs.CV])" — Two methods that step toward a style image independent neural style transfer model which could generate semantically accurate generated images for any content, style image input pair.

Paper: http://arxiv.org/abs/2302.03875
Code: https://github.com/nipdep/STGAN

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
The generated image (c), which …

"TetCNN: Convolutional Neural Networks on Tetrahedral Meshes. (arXiv:2302.03830v1 [cs.CV])" — A novel interpretable graph Convolutional Neural Network (CNN) framework for tetrahedral mesh structures, inspired by ChebyNet.

Paper: http://arxiv.org/abs/2302.03830

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
TetCNN architecture for the cla…

"How to Trust Your Diffusion Model: A Convex Optimization Approach to Conformal Risk Control. (arXiv:2302.03791v1 [stat.ML])" — A focus on image-to-image regression tasks to arrive at a generalization of the Risk-Controlling Prediction Sets (RCPS) procedure, which allows to provide: i) entrywise calibrated intervals for future samples of any diffusion model, ii) control a certain notion of risk with respect to a ground truth image with minimal mean interval length.

Paper: http://arxiv.org/abs/2302.03791

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Example images

Colorful sculpted flowers (?) on the ceiling of the Bellagio Hotel & Casino in 2019 #LasVegas #art #photography

"Understanding Why ViT Trains Badly on Small Datasets: An Intuitive Perspective. (arXiv:2302.03751v1 [cs.CV])" — A visual intuition to help understand why ViT has a significantly lower evaluation accuracy when trained on small datasets when compared to ResNet-18 with a similar number of parameters.

Paper: http://arxiv.org/abs/2302.03751
Code: https://github.com/BoyuanJackChen/Visualize-Transformer-ResNet18

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Visualization for ViT on CIFAR-…