​​NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion

In this paper, Microsoft Research Asia and Peking University researchers share a unified multimodal (texts, images, videos, sketches) pre-trained model called NÜWA that can generate new or manipulate existing visual data for various visual synthesis tasks. Furthermore, they have designed a 3D transformer encoder-decoder framework with a 3D Nearby Attention (3DNA) mechanism to consider the nature of the visual data and reduce the computational complexity.

NÜWA achieves state-of-the-art results on text-to-image generation, text-to-video generation, video prediction, and several other tasks and demonstrates good results on zero-shot text-guided image and video manipulation tasks.

Paper: https://arxiv.org/abs/2111.12417
Code: https://github.com/microsoft/NUWA

A detailed unofficial overview of the paper: https://andlukyane.com/blog/paper-review-nuwa

#deeplearning #cv #transformer #pretraining

📹 End-to-End Referring Video Object Segmentation with Multimodal Transformers

Github: https://github.com/mttr2021/MTTR

Paper: https://arxiv.org/abs/2111.14821v1

Dataset: https://kgavrilyuk.github.io/publication/actor_action/

@ai_machinelearning_big_data

YaTalks — Yandex's conference for IT community.

Yandex will host its traditional conference on 3-4 December (starting tomorrow). Registration is open.

One of the tracks is devoted to Machine/Deep Learning with the focus on content generation.

Featured reports:

📚How too train text model on the minimal corpus
🎙️How Yandex.Browser Machine Translation works
🤖 Facial Expressions Animation

Conference website: https://yatalks.yandex.ru/?from=tg_opendatascience

#conference #mt #nlu

Visual Genome: the most labeled dataset
👁Scientists at Stanford University have collected the most annotated dataset with over 100,000 images. In total, the dataset contains almost 5.5 million object descriptions, attributes and relationships. You don't even have to download the dataset, but get the data you need by accessing the RESTful API endpoint using the GET-method. Despite the fact that the latest updates to the dataset are dated 2017, this is an excellent data set for training models in typical ML problems, from recognizing generated data using graph algorithms.
https://visualgenome.org/api/v0/api_home.html

​​EditGAN: High-Precision Semantic Image Editing

Nvidia researches built an approach for editing segments of a picture with supposedly realtime picture augmentation according to the segment alterations. No demo is available yet though.

All the photoshop power users should relax, because appereance of such a tools means less work for them, not that the demand for the manual retouch will cease.

Website: https://nv-tlabs.github.io/editGAN/
ArXiV: https://arxiv.org/abs/2111.03186

#GAN #Nvidia

Upgini — dataset search automation library

Upgini is a new python library for an automated useful dataset search to boost supervised ML tasks

It enriches your dataset with intelligently crafted features from a broad range of curated data sources, including open and commercial datasets. The search is conducted for any combination of public IDs contained in your tabular dataset: IP, date, etc. Only features that could improve the prediction power of your ML model are returned.

Developers said that they wanted radically simplify data search and delivery for ML pipelines to make external data & features a standard approach. Like a hyperparameter tuning for machine learning nowadays.

A Free 30-days trial is available.

GitHub: https://github.com/upgini/upgini
Web: https://upgini.com

New V3 Silero VAD is Already Here

Main changes

- One VAD to rule them all!
- New model includes the functionality of all of the previous ones with improved quality and speed!
- As far as we know, our VAD is the best in the world now;
- Flexible sampling rate, 8000 Hz and 16000 Hz are supported;
- Flexible chunk size, minimum chunk size is just 30 milliseconds!
- Only 100k parameters;
- GPU inference and batching are supported (the model is small, so we decided not to publish a quantized model);
- Radically, drastically simplified examples;

We also drastically polished and simplified README, wiki and repo in general.

Links:

- Silero VAD repo - https://github.com/snakers4/silero-vad
- The migration to V3 is quite simple, here are some examples
- Quality metrics
- Performance metrics
- Examples and dependencies
- Colab with examples

If you like Silero VAD, please give us a ⭐️ and spread the news!

​​NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation

This paper presents a new participatory Python-based natural language augmentation framework that supports the creation of transformations (modifications to the data) and filters (data splits according to specific features).

The current version of the framework contains 117 transformations and 23 filters for a variety of natural language tasks.

The authors demonstrate the efficacy of NL-Augmenter by using several of its transformations to analyze the robustness of popular natural language models.

Paper: https://arxiv.org/abs/2112.02721
Code: https://github.com/GEM-benchmark/NL-Augmenter

A detailed unofficial overview of the paper: https://andlukyane.com/blog/paper-review-nlaugmenter

#deeplearning #nlp #augmentation #robustness

We continue to conquer the time series together with ETNA! Using our library, we built a model to predict the number of new 🦠COVID-19 cases in different countries. You can see the results we got in our recent article on 📖 Medium: Forecasting with ETNA - Fast and Furious. The article also shows in detail what a typical forecasting pipeline looks like and how you can quickly get a good baseline for a specific dataset. For all questions and suggestions - welcome to ETNA Community in Telegram. For all news related to AI/ML at Tinkoff — stay tuned to this channel.

​​Perceiver IO: a scalable, fully-attentional model that works on any modality

#HuggingFace added neural network which is capable of working on all kinds of modailities: text, images, audio, video, coordinates, etc to the transformers library.

Blog: https://huggingface.co/blog/perceiver

Stats by @TGStat_Bot

All the reactions had been enabled for @opendatascience

We got lot's of fine messages and feedback, let's discuss most notable papers and news of 2021 to assemble Community 2021 WrapUp in our chat:

https://t.iss.one/datascience_chat

2021 WrapUps and Summaries


Those are two technical posts summarizing the progress which were published during 2021.

Papers with Code 2021 : A Year in Review post by Papers with Code

Medium: https://medium.com/paperswithcode/papers-with-code-2021-a-year-in-review-de75d5a77b8b

Post on KDNuggers
Post: https://www.kdnuggets.com/2021/12/2021-year-review-amazing-ai-papers.html

#summary

The Illustrated Retrieval Transformer
by @jayalammar

The latest batch of language models can be much smaller yet achieve GPT-3 like performance by being able to query a database or search the web for information. A key indication is that building larger and larger models is not the only way to improve performance.


https://jalammar.github.io/illustrated-retrieval-transformer/

#nlp #gpt3 #retro #deepmind

🦜 Hi!

We are the first Telegram Data Science channel.

Channel was started as a collection of notable papers, news and releases shared for the members of Open Data Science (ODS) community. Through the years of just keeping the thing going we grew to an independent online Media supporting principles of Free and Open access to the information related to Data Science.


Ultimate Posts

* Where to start learning more about Data Science. https://github.com/open-data-science/ultimate_posts/tree/master/where_to_start
* @opendatascience channel audience research. https://github.com/open-data-science/ods_channel_stats_eda


Open Data Science

ODS.ai is an international community of people anyhow related to Data Science.

Website: https://ods.ai



Hashtags

Through the years we accumulated a big collection of materials, most of them accompanied by hashtags.

#deeplearning #DL — post about deep neural networks (> 1 layer)
#cv — posts related to Computer Vision. Pictures and videos
#nlp #nlu — Natural Language Processing and Natural Language Understanding. Texts and sequences
#audiolearning #speechrecognition — related to audio information processing
#ar — augmeneted reality related content
#rl — Reinforcement Learning (agents, bots and neural networks capable of playing games)
#gan #generation #generatinveart #neuralart — about neural artt and image generation
#transformer #vqgan #vae #bert #clip #StyleGAN2 #Unet #resnet #keras #Pytorch #GPT3 #GPT2 — related to special architectures or frameworks
#coding #CS — content related to software engineering sphere
#OpenAI #microsoft #Github #DeepMind #Yandex #Google #Facebook #huggingface — hashtags related to certain companies
#productionml #sota #recommendation #embeddings #selfdriving #dataset #opensource #analytics #statistics #attention #machine #translation #visualization


Chats

- Data Science Chat https://t.iss.one/datascience_chat
- ODS Slack through invite form at website

ODS resources

* Main website: https://ods.ai
* ODS Community Telegram Channel (in Russian): @ods_ru
* ML trainings Telegram Channel: @mltrainings
* ODS Community Twitter: https://twitter.com/ods_ai

Feedback and Contacts

You are welcome to reach administration through telegram bot: @opendatasciencebot

Highly accurate protein structure prediction with AlphaFold
Anna Potapenko @DeepMind

Predicting a protein’s structure from its primary sequence has been a grand challenge in biology for the past 50 years, holding the promise to bridge the gap between the pace of genomics discovery and resulting structural characterization. In this talk, we will describe work at DeepMind to develop AlphaFold, a new deep learning-based system for structure prediction that achieves high accuracy across a wide range of targets. We demonstrated our system in the 14th biennial Critical Assessment of Protein Structure Prediction (CASP14) across a wide range of difficult targets, where the assessors judged our predictions to be at an accuracy “competitive with experiment” for approximately 2/3rds of proteins. The talk will cover both the underlying machine learning ideas and the implications for biological research.


https://youtu.be/oD34Q1qeMII

Using public datasets in commercial software

Great paper: Can I use this publicly available dataset to build commercial AI software? Most likely not.

An extremely important question for the Data Science community: it turns out (wat?) that not all publicly available datasets can be used to build commercial solutions 💣💣💣.

Authors examine license agreements of 6 popular datasets used in Computer Vision (CIFAR-10, ImageNet, Cityscapes, FFHQ, VGGFaces2 and MS COCO) and conclude that the models trained on these data can not be commercialized at least.

An example of the results of the CIFAR-10 dataset's license analysis is shown in the screenshot.

It was logical to assume this, but for many community members this may be the opening of the century.

Prepared by @codemining for ods.ai. Subscribe!

​​There had been less posts than usual as you might have noticed, only because editor-in-chief's (mine) attention been directed to DeFi space in general and NFT in particular.

However once involved with the beauty of AI and art, one can't just exit it, so I've been working on an NFT-collection drop as an exercise to study the field. Because as Feynman taught us 'What I cannot create, I do not understand'.

After getting some early results with #StyleGAN2 I realised that I need to study how drop mechanics and everything else works and asked a very talented friend to help me with generating the art for the collection. On my humble scale, he is top 0.1% researcher in the field (though he might argue with that, or you might, but let's wait for his scientific papers published here to judge on that), so I was sure that the art will be dope.

And it was so great we decided to make a real NFT drop instead of purely experimental one. Soon we will publish all the intersting technical details on the architecture and approache we used to generate beautiful toadz. So stay tuned for the post on how to generate astonishing art and subsribe to the collection twitter not to miss any details.

Twitter: https://twitter.com/toadverseNFT