That’s the end of another set of paper readings for the week 🙂 9 papers boosted today out of a total of 66 new and updated papers on arXiv.org under the cs.CV category …

See you next week, I guess?

#AI #CV #NewPapers #DeepLearning #MachineLearning

I guess I should start sharing some of my art here. This is a tiny murmuration of birds that I painted for my bird-loving partner. #MastoArt #Art #BirdsOfMastodon

My poor wife has the patience of a saint and I am guilty of such heinous crimes against humanity, that I should have been murdered long ago 😛

Case in point …

My wife says, “There’s a jam jar on the table.” which is code for, “there’s an almost empty jam jar that you can clean out by eating the last of the jam."

Of course, I simply respond with: “There are some boxes on the table.”

She gives me the look that’s reserved just for me — “Are you daft? Or are you intentionally mistaking what I said?” is what it says.

“What? I thought we were making observations,” I respond, smiling innocently 😀

No matter how dark it seems, there is always a path forward.

#Aotearoa #nz #Photography #Nature #naturephotography #LandscapePhotography #NewZealand #LongExposure #astro #astrophotography

New day, new opportunity to share what's good/funny/calming. Nobody here needs convincing there's a whole lot messed up. I have nothing new to add to that discourse. People with far more empathy and wisdom have been voicing what needs to be said. It's up to the rest of us to listen, introspect and apply.

Maybe someday we will see ourselves for who we are - each a unique instance of the same base class - life. Our differences are the spicy exceptions, our similarities, the filling rule.

"UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models. (arXiv:2302.04867v1 [cs.LG])" — A unified corrector (UniC) that can be applied after any existing DPM sampler to increase the order of accuracy without extra model evaluations, and derive a unified predictor (UniP) that supports arbitrary order as a byproduct.

Paper: http://arxiv.org/abs/2302.04867
Code: https://github.com/wl-zhao/UniPC

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
The main idea of UniPC. We prov…

"Trading Information between Latents in Hierarchical Variational Autoencoders. (arXiv:2302.04855v1 [stat.ML])" — A generalization of VAEs to application domains beyond generative modeling (e.g., representation learning, clustering, or lossy data compression) by introducing an objective function that allows practitioners to trade off between the information content ("bit rate") of the latent representation and the distortion of reconstructed data.

Paper: http://arxiv.org/abs/2302.04855

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Left: trade-off between perform…

four seasons: one creek. #photography #YEG #Edmonton

My child told me they need a topic for an argumentative essay they have to write for school.

I am happy to announce they are now writing an essay on how cash bail for non-violent offenses merely serves to deprive the poor of their right to a presumption of innocence and the ability to effectively defend themselves.

Do you have experience in #fairness, #accountability, and #transparency in socio-technical systems? Sign up to join the #FAccT2023 program committee and help shape the future of the field! (@facct) #responsibleAI #AI
https://docs.google.com/forms/d/e/1FAIpQLSc71_qqhSTZ8LF73PGlrOyI--aYeKMUcU8Kxqg_JK6Xv7N78w/viewform

"Robot Synesthesia: A Sound and Emotion Guided AI Painter. (arXiv:2302.04850v1 [cs.CV])" — An approach for using sound and speech to guide a robotic painting process by encoding the simulated paintings and input sounds into the same latent space.

Paper: http://arxiv.org/abs/2302.04850
Code: https://github.com/pschaldenbrand/Frida

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Our robot painting sound guidan…

Good folks of #academia, I am looking for an endorsement to #arxiv in the field of CS.cy - computers and society - to upload a preprint of some work.

My ANU page is:
https://cybernetics.anu.edu.au/people/kathy-reid/

Is there anyone who would be willing to endorse me?

Endorse link is:
https://arxiv.org/auth/endorse?x=LZFMQK

If there's any marginalised people in AU/NZ that need a new home in the wake of the mastodon.lol shutdown, sing out, Cloud Island would be happy to host you.

If you can please boost this. 🙂

"Is This Loss Informative? Speeding Up Textual Inversion with Deterministic Objective Evaluation. (arXiv:2302.04841v1 [cs.CV])" — A study of the training dynamics of textual inversion, with the aim of speeding it up.

Paper: http://arxiv.org/abs/2302.04841

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
A summary of our key findings: …

"Better Diffusion Models Further Improve Adversarial Training. (arXiv:2302.04638v1 [cs.CV])" — Tries to answer the question "Can better diffusion models further improve adversarial training?" empirically.

Paper: http://arxiv.org/abs/2302.04638
Code: https://github.com/wzekai99/DM-Improves-AT

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
A brief summary comparison of t…

Current mastodon.lol members looking for a new home, I’d encourage you to explore https://vmst.io/about and https://docs.vmst.io and see if we might be the place for you.

Feel free to reach out with any questions about site policy, moderation, or help with moving.

"Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples. (arXiv:2302.04578v1 [cs.CV])" — Exploration into creating an image that is similar to another image for human vision, but unrecognizable for diffusion models to investigate the possibility of creating images that hinder diffusion models from extracting their features.

Paper: http://arxiv.org/abs/2302.04578

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Comparison of workflows for adv…

"Efficient Attention via Control Variates. (arXiv:2302.04542v1 [cs.LG])" — A look at control variates to show that Random-Feature-based Attention (RFA) can be decomposed into a sum of multiple control variate estimators for each element in the sequence.

Paper: http://arxiv.org/abs/2302.04542

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Left and middle: empirical memo…

"Feature Likelihood Score: Evaluating Generalization of Generative Models Using Samples. (arXiv:2302.04440v1 [cs.LG])" — A parametric sample-based score that uses density estimation to quantitatively measure the quality/diversity of generated samples of deep generative models while taking overfitting into account.

Paper: http://arxiv.org/abs/2302.04440
Code: https://github.com/marcojira/fls

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
FLS for a generative model that…

"Q-Diffusion: Quantizing Diffusion Models. (arXiv:2302.04304v1 [cs.CV])" — A solution to the slowness in diffusion models to generate images by compressing the noise estimation network to accelerate the generation process using post-training quantization (PTQ).

Paper: http://arxiv.org/abs/2302.04304

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Stable Diffusion 512 ×512 text-…