The Space Needle appears to be taking off from the fog in Seattle, Washington with Mt Rainier on the horizon:

#Photography #SpaceNeedle #MtRainier #WashingtonState

photo by Steve T. Luong
https://stevenluong.darkroom.com/

Someday you will meet someone who laughs at all your jokes. Do not trust this person. They are most likely a spy, or a Scientologist. Your jokes are terrible.

Been switching between several different Mastodon clients recently, trying to figure out what works best for us and so far, I think Tusker (https://apps.apple.com/us/app/tusker/id1498334597) is the one which works the best for my own needs (and that of my wife) …

Some features are a bit harder to find, but the overall app shows a level of care and consideration that indicates that this is an app which has been in development over time and that the developer uses the app personally. It has a lot of the features that I wanted and about the only major thing it’s missing is the ability to edit posts.

I’m using it on macOS as a Catalyst app and there are some minor personal niggles of mine on macOS, but since the source is available, I’ll be making the changes myself (and sharing with the author if they would like to add it to the main app).

For the time being, I think I’m sorted 😛

#MastodonClient #Software #macOS #Tusker

And that's another round of paper reading done! Posted about 9 papers out of 43 in the cs.CV category on arXiv.org today ...

#AI #CV #NewPapers #DeepLearning #MachineLearning

"Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners. (arXiv:2108.13161v7 [cs.CL] CROSS LISTED)" — A novel pluggable, extensible, and efficient large-scale pre-trained language model approach which can convert small language models into better few-shot learners without any prompt engineering.

Paper: http://arxiv.org/abs/2108.13161
Code: https://github.com/zjunlp/DART

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
The architecture of DifferentiA…

"VN-Transformer: Rotation-Equivariant Attention for Vector Neurons. (arXiv:2206.04176v3 [cs.CV] UPDATED)" — A novel "VN-Transformer" architecture to address several shortcomings of the current Vector Neuron (VN) models.

Paper: http://arxiv.org/abs/2206.04176

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
VN-Transformer (“early fusion”)…

"Towards Arbitrary Text-driven Image Manipulation via Space Alignment. (arXiv:2301.10670v1 [cs.CV])" — A new Text-driven image Manipulation framework via Space Alignment (TMSA) which aims to align the same semantic regions in CLIP and StyleGAN spaces so that the text input can be directly accessed into the StyleGAN space and be used to find the semantic shift according to the text description.

Paper: http://arxiv.org/abs/2301.10670

#AI #CV #NewPaper #DeepLearning #MachineLearning

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

"Toward Realistic Evaluation of Deep Active Learning Algorithms in Image Classification. (arXiv:2301.10625v1 [cs.CV])" — An Active Learning (AL) benchmarking suite and a set of extensive experiments on five datasets shedding light on the questions: when and how to apply AL.

Paper: http://arxiv.org/abs/2301.10625

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
The Active Learning loop featur…

"An Efficient Approximate Method for Online Convolutional Dictionary Learning. (arXiv:2301.10583v1 [cs.CV])" — An approximate online convolutional dictionary learning (OCDL) method that incorporates sparse decomposition of the training samples which addresses optimization problems using the alternating direction method of multipliers.

Paper: http://arxiv.org/abs/2301.10583
Code: https://github.com/farshadgveshki/approximate-online-convolutional-dictionary-learning

#AI #CV #NewPaper #DeepLearning #MachineLearning

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

"Variation-Aware Semantic Image Synthesis. (arXiv:2301.10551v1 [cs.CV])" — A new requirement for semantic image synthesis (SIS) to achieve more photorealistic images, variation-aware, which consists of inter- and intra-class variation.

Paper: http://arxiv.org/abs/2301.10551

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Examples of class-level mode co…

"DEJA VU: Continual Model Generalization For Unseen Domains. (arXiv:2301.10418v1 [cs.LG])" — A framework that focuses on improving models' target domain generalization (TDG) capability, while also achieving effective target domain adaptation (TDA) capability right after training on certain domains and forgetting alleviation (FA) capability on past domains.

Paper: http://arxiv.org/abs/2301.10418

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Overview of applying our framew…

"Local Feature Extraction from Salient Regions by Feature Map Transformation. (arXiv:2301.10413v1 [cs.CV])" — A framework that robustly extracts and describes salient local features regardless of changing light and viewpoints by suppressing illumination variations and encouraging structural information to ignore the noise from light and to focus on edges.

Paper: http://arxiv.org/abs/2301.10413

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Proposed framework. Network con…

#notebook #doodle, #ballpoint and #copic

"A Fast Feature Point Matching Algorithm Based on IMU Sensor. (arXiv:2301.10293v1 [cs.CV])" — An algorithm using the inertial measurement unit (IMU) to optimize the efficiency of image feature point matching, in order to reduce the time consumed when matching feature points in simultaneous localization and mapping (SLAM).

Paper: http://arxiv.org/abs/2301.10293

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Two adjacent frames. The left i…

A total of 43 papers in the cs.CV category on arXiv.org today — 33 new, 10 updated.

Onwards to the papers!

#AI #CV #NewPapers #DeepLearning #MachineLearning

We (@emilymbender, @mmitchell_ai and I) are organizing a virtual Stochastic Parrots Day on March 17. We thought it was time for a retrospective, & plan to discuss the current landscape, how we got here & where we need to go instead. Sign up below to join us.
https://www.eventbrite.com/e/stochastic-parrots-day-tickets-524219965027

I'm giving away up to ten copies of my book, A Programmer's Guide to Computer Science. If this would be useful to you but you cannot currently afford it, leave a comment and I'll message you this weekend for your contact information.

With so many places having done layoffs lately, I wanted to mention the US Digital Service is hiring. It's a wild place to work, but also you get to work on legitimately meaningful projects that affect a lot of people (in 2022, we made it easier for transgender ppl to get passports, helped low-income families buy food, and I got to help identify disadvantage communities for environmental funding). I'm happy to talk about USDS if you're on the fence. http://ow.ly/LpqJ50LVnPV #fedihire #fedijobs

Hey all, would appreciate a post boost on this one.

I, unfortunately, got laid off last week and am looking for a new job! If you know of any going that fit my skillset of video content creation, educational CG writing, CG generalist then I'd love to hear about it!

https://www.artstation.com/blenderbrit

Coming to Berlin on June 30th 2023: The Women+ in Data and AI Tech Festival: One day and one night filled with tech talks about #datascience, #machinelearning, and #mlops , empowering off-topic sessions and a huge party at the end. Follow us for updates. Tickets will be available soon 👉 https://women-in-data-ai.tech/