It's #WerewolfWednesday, and I have a story I really wanna share:

In 1691 an 80-something Livonian man named Old Thiess was called to court as a witness in a theft case. As he was sworn in, another witness laughed: "How can he swear a holy oath when everyone knows he is a werewolf?"

The judges immediately forgot about the thief and put Old Thiess on trial. He calmly admitted that yes, indeed he was a werewolf.
1/6

#folklore #werewolves

#introduction radio free fedi is a small web, consent driven, artist populated, non-commercial, attribution promoting, community radio

we are now ready to accept more submissions, and are here to promote sound and music artists, their support links, desired license and fedi presence if they wish in an eclectic and fun radio format

24/7 music from the fedi with "theNews" at the top of each hour

https://radiofreefedi.net

keep fedi weird

#radio #community #fedimusic #fediart #music #art

Today turned out to be a light day for paper reading — only 7 papers in the cs.CV category, and 3 from other categories on arXiv posted.

But hey, the weekend is almost here 😛

#AI #CV #NewPapers #DeepLearning #MachineLearning

Spring in the City
By Sabantha

The Promise - a half opened your sunflower. #Sunflower #Romantic #2023 AYearForArt #BuyArtNotCandy #AYearForArt #JanuaryJoy #Art #Artist #LoveArt #IrisRichardsonArtist #ArtCollector #ArtMatters #mastoart #FediGiftShop
https://www.pictorem.com/598336/Half%20Opened%20Sunflower.html

"Bayesian Metric Learning for Uncertainty Quantification in Image Retrieval. (arXiv:2302.01332v1 [cs.LG])" — A Bayesian encoder for metric learning which, rather than relying on neural amortization as done in prior works, learns a distribution over the network weights with the Laplace Approximation.

Paper: http://arxiv.org/abs/2302.01332

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Reliable stochastic embeddings.…

"Dual PatchNorm. (arXiv:2302.01327v1 [cs.CV])" — Experiments with adding two Layer Normalization layers (LayerNorms), before and after the patch embedding layer in Vision Transformers, to see how it affects accuracy.

Paper: http://arxiv.org/abs/2302.01327

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
The plot displays the accuracy …

@AngelaPreston Yes, I’m not sure if I interpreted it correctly either 🙂 I was going by the middle image where I assumed that the strength of the blue colour indicated the strength of the smell …

But that didn’t seem to totally gel with the third image in terms of it going off course yet again … But since the third image doesn’t have the smell overlay (if that’s indeed what it is …) I can’t be sure that it didn’t again land on a cell with no smell and so went off course again due to the randomness …

@andrey I guess it all depends on what people are looking for. Some just got annoyed at Twitter but they really want what Twitter offers while others (like me) actually find the Fediverse way much better. The former will leave when they can’t get what they want, the latter will (hopefully) stick around 🙂

@AngelaPreston My guess would be that the wrong course was dictated by the randomness — it took one step away from the source and then kept making new turns randomly trying to find a stronger smell “signal”?

"Deep reinforcement learning for the olfactory search POMDP: a quantitative benchmark" — Using deep reinforcement learning to search for a source of odor in turbulence, as applicable to sniffer robots.

Paper: https://arxiv.org/abs/2302.00706

#NewPaper #Robotics #DeepLearning

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

"Why Combining Text and Visualization Could Improve Bayesian Reasoning: A Cognitive Load Perspective" — An examination of the cognitive load elicited when solving Bayesian problems using icon arrays, text, and a juxtaposition of text and icon arrays.

Paper: https://arxiv.org/abs/2302.00707

#NewPaper #HumanComputerInteraction #HC

<<Find this useful? Please boost so that others can benefit too 🙂>>
An illustrative overview of our…

@AngelaPreston Yep .. or at least, that's similar to my thoughts. I guess I expect too much of people and this kind of thing just makes me think way too much about the "why" rather than simply just shrugging it off and moving on 😛

"CrazyChoir: Flying Swarms of Crazyflie Quadrotors in ROS 2" — A modular Python framework based on the Robot Operating System (ROS) 2 which provides a comprehensive set of functionalities to simulate and run experiments on teams of cooperating Crazyflie nano-quadrotors.

Paper: https://arxiv.org/abs/2302.00716

#NewPaper #Robotics

<<Find this useful? Please boost so that others can benefit too 🙂>>
CRAZYCHOIR architecture. Crazyf…

"Real-Time Evaluation in Online Continual Learning: A New Paradigm. (arXiv:2302.01047v1 [cs.LG])" — A practical real-time evaluation of continual learning, in which the stream does not wait for the model to complete training before revealing the next data for predictions.

Paper: http://arxiv.org/abs/2302.01047

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
OCL Real-Time Evaluation Exampl…

"Multimodal Chain-of-Thought Reasoning in Language Models. (arXiv:2302.00923v1 [cs.CL])" — A Multimodal Chain-of-Thought that incorporates vision features in a decoupled training framework which separates the rationale generation and answer inference into two stages and incorporates vision features in both stages.

Paper: http://arxiv.org/abs/2302.00923

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Example of the multimodal CoT t…

"Language Quantized AutoEncoders: Towards Unsupervised Text-Image Alignment. (arXiv:2302.00902v1 [cs.LG])" — A modification of VQ-VAE that learns to align text-image data in an unsupervised manner by leveraging pretrained language models (e.g., BERT, RoBERTa).

Paper: http://arxiv.org/abs/2302.00902

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Language Quantization AutoEnco…

"Disentanglement of Latent Representations via Sparse Causal Interventions. (arXiv:2302.00869v1 [cs.LG])" — A new method for disentanglement inspired by causal dynamics that combines causality theory with vector-quantized variational autoencoders where the model considers the quantized vectors as causal variables and links them in a causal graph.

Paper: http://arxiv.org/abs/2302.00869

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Atomic interventions on one fac…

"SHINE: Deep Learning-Based Accessible Parking Management System. (arXiv:2302.00837v1 [cs.CV])" — A system which uses deep learning object detection algorithms to detect the vehicle, license plate, and disability badges and then authenticates the rights to use the accessible parking spaces by coordinating with a central server.

Paper: http://arxiv.org/abs/2302.00837

#AI #CV #NewPaper #DeepLearning #MachineLearning

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

A total of 72 papers in the cs.CV category on arXiv.org today — 56 new, 16 updated.

Let’s read some papers!

#AI #CV #NewPapers #DeepLearning #MachineLearning