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 …

"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