home.social

#imagenet — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #imagenet, aggregated by home.social.

fetched live
  1. 📉🤖 Oh, look! Another treatise on why #academia swapped out rational math for the lazy allure of "good enough" #AI. Apparently, #ImageNet and the irresistible siren call of not specifying goals have won over academia's finest. Way to go, Guy Freeman, for enlightening us on how to achieve #mediocrity in the most complex way possible. 🎓💡
    gfrm.in/posts/why-decision-the #rationality #innovation #HackerNews #ngated

  2. Ведущий разработчик ChatGPT и его новый проект — Безопасный Сверхинтеллект

    Многие знают об Илье Суцкевере только то, что он выдающийся учёный и программист, родился в СССР, соосновал OpenAI и входит в число тех, кто в 2023 году изгнал из компании менеджера Сэма Альтмана. А когда того вернули, Суцкевер уволился по собственному желанию в новый стартап Safe Superintelligence («Безопасный Сверхинтеллект»). Илья Суцкевер действительно организовал OpenAI вместе с Маском, Брокманом, Альтманом и другими единомышленниками, причём был главным техническим гением в компании. Ведущий учёный OpenAI сыграл ключевую роль в разработке ChatGPT и других продуктов. Сейчас Илье всего 38 лет — совсем немного для звезды мировой величины.

    habr.com/ru/companies/ruvds/ar

    #Илья_Суцкевер #Ilya_Sutskever #OpenAI #10x_engineer #AlexNet #Safe_Superintelligence #ImageNet #неокогнитрон #GPU #GPGPU #CUDA #компьютерное_зрение #LeNet #Nvidia_GTX 580 #DNNResearch #Google_Brain #Алекс_Крижевски #Джеффри_Хинтон #Seq2seq #TensorFlow #AlphaGo #Томаш_Миколов #Word2vec #fewshot_learning #машина_Больцмана #сверхинтеллект #GPT #ChatGPT #ruvds_статьи

  3. #ConvolutionalNeuralNetworks (#CNNs in short) are immensely useful for many #imageProcessing tasks and much more...

    Yet you sometimes encounter some bits of code with little explanation. Have you ever wondered about the origins of the values for image normalization in #imagenet ?

    • Mean: [0.485, 0.456, 0.406] (for R, G and B channels respectively)
    • Std: [0.229, 0.224, 0.225]

    Strangest to me is the need for a three-digits precision. Here, after finding the origin of these numbers for MNIST and ImageNet, I am testing if that precision is really important : guess what, it is not (so much) !

    👉 if interested in more details, check-out laurentperrinet.github.io/scib

  4. How a stubborn #computerscientist accidentally launched the #deeplearning boom
    "You’ve taken this idea way too far," a mentor told Prof. Fei-Fei Li, who was creating a new image #dataset that would be far larger than any that had come before: 14 million images, each labeled with one of nearly 22,000 categories. Then in 2012, a team from Univ of Toronto trained a #neura network on #ImageNet, achieving unprecedented performance in image recognition, dubbed #AlexNet.
    arstechnica.com/ai/2024/11/how #AI

  5. #AI heroic stories and underpaid labour:

    "The project was saved when Li learned about Amazon Mechanical Turk, a crowdsourcing platform Amazon had launched a couple of years earlier. "

    #Imagenet....How a stubborn computer scientist accidentally launched the deep learning boom - Ars Technica
    arstechnica.com/ai/2024/11/how

  6. 🚀 New #AI Research: Simplified Continuous-time Consistency Models (#sCM)

    🔬 Key findings:
    #OpenAI's new approach matches leading #diffusion models' quality using only 2 sampling steps
    • 1.5B parameter model generates samples in 0.11 seconds on single #GPU
    • Achieves ~50x wall-clock speedup compared to traditional methods
    • Uses less than 10% of typical sampling compute while maintaining quality

    🎯 Technical highlights:
    • Simplifies theoretical formulation of continuous-time consistency models
    • Successfully scaled to 1.5B parameters on #ImageNet at 512×512 resolution
    • Demonstrates consistent performance scaling with teacher diffusion models
    • Enables real-time generation potential for images, audio, and video

    📄 Learn more: openai.com/index/simplifying-s

  7. "#AI is “promising” nothing. It is #people who are promising – or not promising. AI is a piece of software. It is made by people, deployed by people and #governed by people... in terms of urgency, I’m more concerned about ameliorating the risks that are here and now [than by the risks of the techbro SkyNet singularity]."

    — Fei-Fei Li, creator of #ImageNet, whose memoir "The Worlds I See" is out now.

    theguardian.com/technology/202

  8. @lowd I remember when most ML applications were variations on #MNIST. And #Imagenet, but I only had enough computer at the time to play around with Mnist. But yea, even then "Recommendation Engines" were starting to be the first things anyone mentioned because it was low hanging fruit - something of immediately obvious commercial value with terrific training data and an easy task for deployment.

  9. Re-reading 'On the genealogy of machine learning datasets: A critical history of ImageNet' by @alexhanna. So clear the LLM debacle goes back to the start of the DL boom; it's data fetish, flat universalism, social illiteracy & contempt for workers journals.sagepub.com/doi/full/
    #AI #datasets #Imagenet #resistingAI

  10. Exploring ImageNet's influence in digital humanities and art curation:
    The Curator's Machine project delves into how this dataset shapes relationships in the art world. By analyzing its absence of 'art' classification, lack of historical context, and texture vs. outline focus, this research bridges art history, coding, and digital humanities. 🎨🖥️
    by @databasecultures

    #DigitalHumanities #DigitalArtHistory #ImageNet
    dahj.org/article/why-so-many-w

  11. #AI #DeepLearning isn't as fascinating as many people believe. Image recognition AIs, for instance, mostly rely on #ImageNet which has 14 million hand classified images. This mean AI's can at best perceive reality as good as humans can. Of course, they are faster and more accurate. However, AIs can never see through reality beyond human visual perception and classification, at least not Deep Learning #ais

    paperswithcode.com/dataset/ima

  12. A DNN Optimizer that Improves over AdaBelief by Suppression of the Adaptive Stepsize Range

    Guoqiang Zhang, Kenta Niwa, W. Bastiaan Kleijn

    Action editor: Rémi Flamary.

    openreview.net/forum?id=VI2JjI

    #optimizers #imagenet #optimizer

  13. Efficient Inference With Model Cascades

    Luzian Lebovitz, Lukas Cavigelli, Michele Magno, Lorenz K Muller

    Action editor: Yarin Gal.

    openreview.net/forum?id=obB415

    #imagenet #benchmark #models

  14. Learned Thresholds Token Merging and Pruning for Vision Transformers

    Maxim Bonnaerens, Joni Dambre

    Action editor: Mathieu Salzmann.

    openreview.net/forum?id=WYKTCK

    #imagenet #pruning #masking

  15. Optimizing Learning Rate Schedules for Iterative Pruning of Deep Neural Networks

    Shiyu Liu, Rohan Ghosh, John Chong Min Tan, Mehul Motani

    Action editor: Mingsheng Long.

    openreview.net/forum?id=nGW2Ho

    #pruning #imagenet #subnetworks

  16. Foiling Explanations in Deep Neural Networks

    Snir Vitrack Tamam, Raz Lapid, Moshe Sipper

    Action editor: Jakub Tomczak.

    openreview.net/forum?id=wvLQMH

    #adversarial #imagenet #inception

  17. Can we please, as people who work with large public #datasets, start using torrents? I am just simply trying to find an old version of the #ImageNet Object Detection from Video dataset, and all of the links are broken! For multiple years! Another ImageNet dataset I’m downloading is downloading at 500KB/s.

    People have clearly been looking for and using these datasets, and now I need to retrain something and I’m without them. We need to band together and start a torrent tracker for datasets so that we don’t need to rely on one website to download from. With proper permission from the dataset owners of course…

    I’m so committed I might buy my own domain and start hosting a torrent tracker. Anyone interested?

    #DataScience #DataEngineer #MachineLearning #BigData #torrents #torrenting #archiving #archivist

  18. Contrastive Attraction and Contrastive Repulsion for Representation Learning

    Huangjie Zheng, Xu Chen, Jiangchao Yao et al.

    Action editor: Yanwei Fu.

    openreview.net/forum?id=f39UID

    #softmax #representations #imagenet

  19. #DeepLearning is fun sometimes, especially when you play with #ImageNet...

    Here is one result of (our modified version of) ResNet which gives a wrong answer compared to the ground truth label, yet it is visually accurate.

    A warning for us all that the objective is not just to reach the highest accuracy, more to better understand what is going on...

    👉 This was a result obtained by Emmanuel Daucé from Aix Marseille Université, in a joint work with @jnjer and myself.

  20. Supervised Knowledge May Hurt Novel Class Discovery Performance

    ZIYUN LI, Jona Otholt, Ben Dai, Di Hu, Christoph Meinel, Haojin Yang

    Action editor: Vikas Sindhwani.

    openreview.net/forum?id=oqOBTo

    #supervised #labeled #imagenet

  21. Training with Mixed-Precision Floating-Point Assignments

    Wonyeol Lee, Rahul Sharma, Alex Aiken

    Action editor: Nadav Cohen.

    openreview.net/forum?id=ZoXi7n

    #precision #imagenet #floats

  22. Guillotine Regularization: Why removing layers is needed to improve generalization in Self-Superv...

    Florian Bordes, Randall Balestriero, Quentin Garrido, Adrien Bardes, Pascal Vincent

    Action editor: Jinwoo Shin.

    openreview.net/forum?id=ZgXfXS

    #regularization #imagenet #generalization