Posts
1576
Following
139
Followers
878
I'm a bit of an eclectic mess ๐Ÿ™‚ I've been a programmer, journalist, editor, TV producer, and a few other things.

I'm currently working on my second novel which is complete, but is in the edit stage. I wrote my first novel over 20 years ago but then didn't write much till now.

I post about #Coding, #Flutter, #Writing, #Movies and #TV. I'll also talk about #Technology, #Gadgets, #MachineLearning, #DeepLearning and a few other things as the fancy strikes ...

Lived in: ๐Ÿ‡ฑ๐Ÿ‡ฐ๐Ÿ‡ธ๐Ÿ‡ฆ๐Ÿ‡บ๐Ÿ‡ธ๐Ÿ‡ณ๐Ÿ‡ฟ๐Ÿ‡ธ๐Ÿ‡ฌ๐Ÿ‡ฒ๐Ÿ‡พ๐Ÿ‡ฆ๐Ÿ‡ช๐Ÿ‡ซ๐Ÿ‡ท๐Ÿ‡ช๐Ÿ‡ธ๐Ÿ‡ต๐Ÿ‡น๐Ÿ‡ถ๐Ÿ‡ฆ๐Ÿ‡จ๐Ÿ‡ฆ

Fahim Farook

"What do we learn? Debunking the Myth of Unsupervised Outlier Detection. (arXiv:2206.03698v2 [cs.CV] UPDATED)" โ€” An investigation into what Auto-Encoders (AE) actually learn when they are posed to solve two different tasks and challenging the assumption that AEs are likely to be even better at reconstructing some types of Out-of-Distribution (OoD) samples.

Paper: http://arxiv.org/abs/2206.03698

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too ๐Ÿ™‚>>
Unsupervised outlier detection โ€ฆ
0
2
0

Fahim Farook

"Improved Vector Quantized Diffusion Models. (arXiv:2205.16007v2 [cs.CV] UPDATED)" โ€” Two techniques to improve the sample quality of VQ-Diffusion. 1) Explore classifier-free guidance sampling for discrete denoising diffusion models to propose a more general and effective implementation of classifier-free guidance. 2) Use a high-quality inference strategy to alleviate the joint distribution issue in VQ-Diffusion.

Paper: http://arxiv.org/abs/2205.16007
Code: https://github.com/microsoft/vq-diffusion
Demos: https://huggingface.co/spaces/patrickvonplaten/vq-vs-stable-diffusion
https://huggingface.co/spaces/williamberman/vq-diffusion

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too ๐Ÿ™‚>>
In-the-wild text-to-image synthโ€ฆ
0
1
0

this is one of my favorite pictures i've taken. it's hard to see when not zoomed in but above this little there's a grasshopper sitting on a leaf. i love a good bogo deal.

3
7
1

Fahim Farook

โ€œMining Effective Features Using Quantum Entropy for Humor Recognitionโ€ โ€” A paper which looks at dividing a joke into two components โ€” the setup and the punchline โ€” and examining the possible semantics and relationships between these components.

Paper: https://arxiv.org/abs/2302.03716

#NewPaper #Language #Computation

<<Find this useful? Please boost so that others can benefit too ๐Ÿ™‚>>
A humor and non-humor example cโ€ฆ
0
1
0

Fahim Farook

"STILL AROUND": Experiences and Survival Strategies of Veteran Women Software Developers
โ€” 14 interviews to examine the experiences of people at the intersection of ageism and sexism to see how these factors can create a hostile environment for veteran software developers belonging to marginalized genders.

Paper: https://arxiv.org/abs/2302.03723

#NewPaper #SoftwareEngineering

<<Find this useful? Please boost so that others can benefit too ๐Ÿ™‚>>
0
1
0

Sitting with a warm, furry, relaxed puppy on your lap is the absolute best way to wait for the sun to set.
For your viewing pleasure, here is the sunset on the beautiful north coast of California. Almost in real time.
Mastodon was a great find for me when I needed an outlet most.
Sending feel-good vibes your way.

0
3
0

Fahim Farook

"Zero-shot Generation of Coherent Storybook from Plain Text Story using Diffusion Models. (arXiv:2302.03900v1 [cs.CV])" โ€” A neural pipeline for generating a coherent storybook from the plain text of a story by leveraging a combination of a pre-trained Large Language Model and a text-guided Latent Diffusion Model to generate coherent images.

Paper: http://arxiv.org/abs/2302.03900

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too ๐Ÿ™‚>>
Zero-shot generation example ofโ€ฆ
0
1
0

Fahim Farook

"Neural Artistic Style Transfer with Conditional Adversaria. (arXiv:2302.03875v1 [cs.CV])" โ€” Two methods that step toward a style image independent neural style transfer model which could generate semantically accurate generated images for any content, style image input pair.

Paper: http://arxiv.org/abs/2302.03875
Code: https://github.com/nipdep/STGAN

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too ๐Ÿ™‚>>
The generated image (c), which โ€ฆ
0
1
1

Fahim Farook

"TetCNN: Convolutional Neural Networks on Tetrahedral Meshes. (arXiv:2302.03830v1 [cs.CV])" โ€” A novel interpretable graph Convolutional Neural Network (CNN) framework for tetrahedral mesh structures, inspired by ChebyNet.

Paper: http://arxiv.org/abs/2302.03830

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too ๐Ÿ™‚>>
TetCNN architecture for the claโ€ฆ
0
2
1

Fahim Farook

"How to Trust Your Diffusion Model: A Convex Optimization Approach to Conformal Risk Control. (arXiv:2302.03791v1 [stat.ML])" โ€” A focus on image-to-image regression tasks to arrive at a generalization of the Risk-Controlling Prediction Sets (RCPS) procedure, which allows to provide: i) entrywise calibrated intervals for future samples of any diffusion model, ii) control a certain notion of risk with respect to a ground truth image with minimal mean interval length.

Paper: http://arxiv.org/abs/2302.03791

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too ๐Ÿ™‚>>
Example images
0
0
0

Colorful sculpted flowers (?) on the ceiling of the Bellagio Hotel & Casino in 2019

0
4
1

Fahim Farook

"Understanding Why ViT Trains Badly on Small Datasets: An Intuitive Perspective. (arXiv:2302.03751v1 [cs.CV])" โ€” A visual intuition to help understand why ViT has a significantly lower evaluation accuracy when trained on small datasets when compared to ResNet-18 with a similar number of parameters.

Paper: http://arxiv.org/abs/2302.03751
Code: https://github.com/BoyuanJackChen/Visualize-Transformer-ResNet18

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too ๐Ÿ™‚>>
Visualization for ViT on CIFAR-โ€ฆ
0
1
0

Fahim Farook

"Towards causally linking architectural parametrizations to algorithmic bias in neural networks. (arXiv:2302.03750v1 [cs.CV])" โ€” A causal framework for linking an architectural hyperparameter to algorithmic bias to study effect of hyperparameters on inducing biases.

Paper: http://arxiv.org/abs/2302.03750

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too ๐Ÿ™‚>>
The deep learning model developโ€ฆ
0
1
0

Fahim Farook

A total of 71 papers in the cs.CV category on arXiv.org today โ€” 45 new, 26 updated.

On with the reading!

#AI #CV #NewPapers #DeepLearning #MachineLearning
0
0
0

This is why I always carry cash.
https://patreon.com/lowqualityfacts

0
1
0

Hatching a Teeny Tiny Zebra Finch. Great little video featuring the incubation of an abandoned egg and the hatching of a bird smaller than a human fingernail. I was riveted by the birth and first feeding. https://kottke.org/23/02/hatching-a-teeny-tiny-zebra-finch

1
2
0

Not to brag, but I was spewing out hilariously incorrect information before huge tech companies decided to create AI chatbots and ruin the internet.

8
9
1

I've always wondered why barns are red.
https://patreon.com/lowqualityfacts

5
2
0

People who don't speak a word of German are far too confident in their ability to assassinate baby Hitler if given the opportunity to time travel.

0
2
0
Show older