"I²SB: Image-to-Image Schrödinger Bridge. (arXiv:2302.05872v1 [cs.CV])" — A new class of conditional diffusion models that directly learn the nonlinear diffusion processes between two given distributions.

Paper: http://arxiv.org/abs/2302.05872

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Outputs of our proposed Image-t…

"Heckerthoughts" — A manuscript going through the basic concepts central to AI and Machine Learning where the author claims that some concepts he included are missing from modern ML courses. Conversational style, anecdotal, and not too long at 54 pages. Worth reading …

Paper: https://arxiv.org/abs/2302.05449

#AI #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
The “burst” of emails that prom…

"Stochastic Surprisal: An inferential measurement of Free Energy in Neural Networks. (arXiv:2302.05776v1 [cs.LG])" — A framework that allows for action during inference in supervised neural networks.

Paper: http://arxiv.org/abs/2302.05776
Code: https://github.com/olivesgatech/Stochastic-Surprisal

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Stochastic surprisal answers co…

"Adding Conditional Control to Text-to-Image Diffusion Models. (arXiv:2302.05543v1 [cs.CV])" — A method to control pretrained large diffusion models to support additional input conditions which can be used to augment existing generative models such as StableDiffusion by enabling conditional inputs like edge maps, segmentation maps, keypoints, etc.

Paper: http://arxiv.org/abs/2302.05543
Code: https://github.com/lllyasviel/ControlNet

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Control Stable Diffusion with C…

"MaskSketch: Unpaired Structure-guided Masked Image Generation. (arXiv:2302.05496v1 [cs.CV])" — An image generation method that uses a guiding sketch to generate realistic images that match the structure of the sketch.

Paper: http://arxiv.org/abs/2302.05496

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Given an input sketch and its c…

"Element-Wise Attention Layers: an option for optimization. (arXiv:2302.05488v1 [cs.LG])" — A new method of attention mechanism which uses matrices multiplications and has shown 92% accuracy and a 97% reduction in parameters for the Fashion MNIST dataset.

Paper: http://arxiv.org/abs/2302.05488

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
The outputs of the attention mo…

A total of 97 papers in the cs.CV category on arXiv.org today — 40 new, 57 updated.

That seems a little daunting today since there’s other stuff I want to work on too, but I guess we’ll just have to see how many interesting papers there are out of the lot?

#AI #CV #NewPapers #DeepLearning #MachineLearning

Morning all,

I wish you all a happy Monday.

A shot of a beautiful little Robin for todays image, the local nature reserve has many of these at this time of year, and they are all fearless, happy to get really close.

#DailyPhoto #Photography #Nautre #Robin

in another entry for #OopsAllMourningDoves i give you this very nice mourning dove sitting on the edge of a platform bird feeder. all birds are good birds, even the ones that may normally get overlooked or are rather common where you are

#birds #BirdsOfMastodon #BirdPhotography #MourningDove

This is reasonable.
https://patreon.com/lowqualityfacts

New preprint "Opaque prior distributions in Bayesian latent variable models", where we describe issues with priors that are easy to overlook and that can lead to incorrect or irreproducible results. The paper is informed by mistakes that I've made over the years. #sem #bayes #mcmc #stan

https://arxiv.org/abs/2301.08667

Noa Kallioinen gave a short tutorial on how to do prior and likelihood sensitivity analysis (prior sensitivity can be due to prior-likelihood conflict or due to a weak likelihood) with `priorsense` R package in Bayes@Lund and the 18min video is now available https://www.youtube.com/watch?v=TBXD3HjcIps&list=PLUEhQLNNQrgndd7_ZY-U5x9lYssl25jmd&index=13

#Bayes #Stan #RStats

Arcades never died. They just returned to the wild

#aiart #midjourney #midjourneyphotography

James Cameron is a genius.
https://patreon.com/lowqualityfacts

That feeling when he says you look angelic but you don’t know if he means you look really pretty or if you have an abnormally high number of eyeballs.

Art Nouveau style spacesuit with helmet
Midjourney 4 AI Art
#stablediffusion #dalle2 #dalle #aiart #nightcafe #midjourney

Colorful Baby Salamander
Midjourney 4 AI Art
#stablediffusion #dalle2 #dalle #aiart #nightcafe #midjourney

I haven't been posting any #StableDiffusion images since I was busy coding and writing and doing other stuff ...

But I've been generating images. These are from prompts ranging from "a cross between an egg and a rabbit" to "a creature with a large white egg as its body, white rabbit ears, a whiskered face, and rabbit paws and legs, blue sky with clouds, lots of trees in the background" ...

I was trying to get one image to match a story I was writing but I had to try various prompts to get something I was even happy with. And in the end, I didn't use any of these images 😛

#AIArt #StableDiffusion #DeepLearning #MachineLearning #CV #AI
Prompt: “a cross between an egg…
Prompt: “a creature with a larg…
Prompt: “a creature with a larg…
Prompt: “a creature with a larg…

And that’s the start of another week of new paper reading — boosted 8 papers out of a total of 84 new and updated papers in the cs.CV category on arXiv.org

That feels like a whole lot of papers today … just another Monday, eh? 😛

#AI #CV #NewPapers #DeepLearning #MachineLearning

"Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training. (arXiv:2210.07688v2 [cs.CL] UPDATED)" — A study of the object hallucination problem in large-scale Vision-Language Pre-trained (VLP) models from multiple aspects.

Paper: http://arxiv.org/abs/2210.07688
Code: No code in linked repo

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Comparison of image captioning …