Sunset in the Rocky Mountains
By David Lloyd Glover

#art #painting #mastoart #sunset #mountains

I believe that #Buzzards are doing very well over here... No hike without an encounter.

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

line
bend
extrude
repeat
.js

Interior Mars habitat designed by Gustav Klimt
Midjourney 4 AI Art
#stablediffusion #dalle2 #dalle  #aiart #nightcafe #midjourney​

Mars habitat designed by Gustav Klimt
Midjourney 4 AI Art
#stablediffusion #dalle2 #dalle  #aiart #nightcafe #midjourney​

Starship Toad
Midjourney 4 AI Art
#stablediffusion #dalle2 #dalle #aiart #nightcafe #midjourney

I have been doing art the last month. I just got lost in terms of what I did when and tracking all that, which I do more for me than anyone else to track progress and such. Hopefully, I'll get some kind of record together today or tomorrow.

Meanwhile, I'm working on this for the hubs @f. At his request. I have not used animal fur brushes in Procreate before and I have almost zero experience in creating my own weird imaginary creatures, so this should be interesting. I do not promise good! LOL

#ArtMatters #AYearForArt #Procreate #ProcreateArt #DigitalArt #WomensArt #WomenArtists #ArtistsOnMastodon
A screenshot of the Procreate i…

There are several macOS #StableDiffusion GUIs (besides the web GUIs) out there:

1. Diffusion Bee: https://github.com/divamgupta/diffusionbee-stable-diffusion-ui — the grand-daddy of them all since it has been around since the early days.

2. Swift CoreML Diffusers: https://github.com/huggingface/swift-coreml-diffusers — the original CoreML GUI from HuggingFace which started out a new bunch of UIs.

3. MochiDiffusion: https://github.com/godly-devotion/MochiDiffusion — based on the codebase for #2 but now seems to be hard-forked.

4. Ink Bot: https://testflight.apple.com/join/40gExWSM — No website for the app, only the TestFlight page and some info on Mastodon.

I’ve tried all of the above and have even done my own fork of #2 and added my own features: https://github.com/FahimF/swift-coreml-diffusers/

But of the lot, I think I like Ink Bot the best … provided it had a few more features/tweaks. Unfortunately, since it’s closed source, I can’t modify the code to add the features I want 😛

So either I have to go back to my fork of the HuggingFace UI, or start with one of the other options and add the features I want. But I’m still working on my fork of Tusker (Fediverse client in case the sudden segue is confusing …) to add the features I want there … And I want the weekend for reading/writing.

What do do? I don’t know … The urge to code is hard 😜

And that's a wrap with 11 out of 76 new and updated papers on arXiv under the cs.CV category posted today.

See y'all tomorrow 🙂

#AI #CV #NewPapers #DeepLearning #MachineLearning

"Fast Sampling of Diffusion Models via Operator Learning. (arXiv:2211.13449v2 [cs.LG] UPDATED)" — Accelerating the sampling process of diffusion models using neural operators, an efficient method to solve the probability flow differential equations.

Paper: http://arxiv.org/abs/2211.13449

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Illustration of the architectur…

"Diffusion-based Image Translation using Disentangled Style and Content Representation. (arXiv:2209.15264v2 [cs.CV] UPDATED)" — A novel diffusion-based unsupervised image translation method using disentangled style and content representation inspired by the splicing Vision Transformer.

Paper: http://arxiv.org/abs/2209.15264
Code: https://github.com/cyclomon/DiffuseIT

#AI #CV #NewPaper #DeepLearning #MachineLearning

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

"Stable Target Field for Reduced Variance Score Estimation in Diffusion Models. (arXiv:2302.00670v1 [cs.LG])" — A method to improve diffusion models by by reducing the variance of the training targets in their denoising score-matching objective. This is achieved by incorporating a reference batch which is used to calculate weighted conditional scores as more stable training targets.

Paper: http://arxiv.org/abs/2302.00670
Code: https://github.com/Newbeeer/stf

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Illustration of differences bet…

"Continuous U-Net: Faster, Greater and Noiseless. (arXiv:2302.00626v1 [cs.CV])" — A novel family of networks for image segmentation which is a continuous deep neural network that introduces new dynamic blocks modelled by second order ordinary differential equations to overcome some of the limitations in current U-Net architectures.

Paper: http://arxiv.org/abs/2302.00626

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Visual comparison of our contin…

"Inching Towards Automated Understanding of the Meaning of Art: An Application to Computational Analysis of Mondrian's Artwork. (arXiv:2302.00594v1 [cs.CV])" — An attempt to identify capabilities that are related to semantic processing, a current limitation of Deep Neural Networks (DNN), which identifies the missing capabilities by comparing the process of understanding Mondrian's paintings with the process of understanding electronic circuit designs, another creative problem solving instance.

Paper: http://arxiv.org/abs/2302.00594

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Possible cognitive architecture…

"EfficientRep:An Efficient Repvgg-style ConvNets with Hardware-aware Neural Network Design. (arXiv:2302.00386v1 [cs.CV])" — A hardware-efficient architecture of convolutional neural network, which has a repvgg-like architecture which is high-computation hardware(e.g. GPU) friendly.

Paper: http://arxiv.org/abs/2302.00386

#AI #CV #NewPaper #DeepLearning #MachineLearning

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

"Alphazzle: Jigsaw Puzzle Solver with Deep Monte-Carlo Tree Search. (arXiv:2302.00384v1 [cs.CV])" — A reassembly algorithm based on single-player Monte Carlo Tree Search (MCTS) which shows the importance of MCTS and the neural networks working together.

Paper: http://arxiv.org/abs/2302.00384

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Example of a jigsaw puzzle task…

"Detection of Tomato Ripening Stages using Yolov3-tiny. (arXiv:2302.00164v1 [cs.CV])" — A computer vision system to detect tomatoes at different ripening stages by using a neural network-based model for tomato classification and detection.

Paper: http://arxiv.org/abs/2302.00164

#AI #CV #NewPaper #DeepLearning #MachineLearning

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

"Real Estate Property Valuation using Self-Supervised Vision Transformers. (arXiv:2302.00117v1 [cs.CV])" — A new method for property valuation that utilizes self-supervised vision transformers and hedonic pricing models trained on real estate data to estimate the value of a given property.

Paper: http://arxiv.org/abs/2302.00117

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Some sample images from a repre…

"Debiasing Vision-Language Models via Biased Prompts. (arXiv:2302.00070v1 [cs.LG])" — A general approach for debiasing vision-language foundation models by projecting out biased directions in the text embedding by debiasing only the text embedding with a calibrated projection matrix to yield robust classifiers and fair generative models.

Paper: http://arxiv.org/abs/2302.00070
Code: https://github.com/chingyaoc/debias_vl

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Bias of Generative Models. The …

"NASiam: Efficient Representation Learning using Neural Architecture Search for Siamese Networks. (arXiv:2302.00059v1 [cs.CV])" — A novel approach that uses differentiable NAS to improve the multilayer perceptron projector and predictor (encoder/predictor pair) architectures inside siamese-networks-based contrastive learning frameworks (e.g., SimCLR, SimSiam, and MoCo) while preserving the simplicity of previous baselines.

Paper: http://arxiv.org/abs/2302.00059

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Layout of the NASiam architectu…