Deep Learning News 🧠

Share information about #Deeplearning #AI #ArtificialIntelligence #ML #Machinelearning

[AK @_akhaliq]

YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
abs: https://t.co/424f8imHe3
github: https://t.co/FElT8fOBUZ

[AK @_akhaliq]

AnimeSR: Learning Real-World Super-Resolution Models for Animation Videos
abs: https://t.co/EWNa1Etxph

[Deep Learning News 🧠 @Deeplearning_AI]

Best Deep Learning Research of 2021 So Far - OpenDataScience #AI
https://t.co/aaMOPasb0Z

[Doron Adler @Norod78]

Try to make faces look like "vintage magazine shots". Not so happy with these results, people loose to much of their "identity" in the transition.
I've made a horizontal Youtube version here: https://t.co/yDnnntxbYc

[CNET @CNET]

Y'all. This car is capable of driving on highly congested streets. So it drove through New York City.

[AI at Meta @AIatMeta]

We’re sharing significantly improved Mask R-CNN baselines that match recent SOTA results from other #computervision experts. We’re also providing an analysis of what drove these gains & adding recipes to our open source Detectron2 object detection library. https://t.co/BDMR8XijES

[#CVPR2026 @CVPR]

The #CVPR2021 candidates for Best Paper can be found here: https://t.co/7bGyNWVHnI Congratulations to all of the authors whose papers are in contention!

[Deep Learning News 🧠 @Deeplearning_AI]

China‘s AI engineer comes up with Self-driving bicycles!
#AI #ArtificialIntelligence #machinelearning #automotive #technology #innovation #iot

[𝙈𝘼𝙍𝙄𝙉𝘼🦋 @m__sb04]

中国のAIエンジニアの動画コンテンツがレベル高すぎる件🇨🇳
bilibiliで90万人以上のフォロワーを持つ稚晖が4ヶ月で自動運転自転車を作ってしまった回🚲
（チップはHuaweiのAscend 310を使ってる）
https://t.co/i9a4Yi9l2F
https://t.co/Q5vfIy0C9s

[AK @_akhaliq]

Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation
pdf: https://t.co/jSCe3uC4CF
abs: https://t.co/4cizwx2IAw
github: https://t.co/VQBGgDloRZ
project page: https://t.co/4xDQubvxID

[AI at Meta @AIatMeta]

Today, we’re introducing TextStyleBrush, the first self-supervised AI model that replaces text in existing images of both scenes and handwriting — in one shot — using just a single example word: https://t.co/0QfLraAQvV

[Weidi Xie @WeidiXie]

Code:

Self-supervised Video Object Segmentation by Motion Grouping:

https://t.co/OwWYjO7c4R

We show that self-supervised segmentation can be done purely motions.

[Deep Learning News 🧠 @Deeplearning_AI]

＼Free Webinar／ On Wednesday, May 26 and Thursday, June 3, LeapMind will be holding a free online seminar entitled “Edge #AI Video Noise Reduction - From Still Image to Video. Register now!!
#machinelearning #technology #deeplearning #computervision #semi
https://t.co/sMOUhvCCkU

[Antonio Grasso @antgrasso]

Since no customers will have to forego their favorite bread, and no baker will have to produce more bread than necessary, Baking on Demand has the advantage of reducing food waste.

My article > https://t.co/6tp4nVrUEj @insightdottech @Inteliot via @antgrasso #IntelPartner #AI

[Deep Learning News 🧠 @Deeplearning_AI]

AI 50: America’s Most Promising Artificial Intelligence Companies
#AI50 @Forbes
https://t.co/ZAY2WrdEUh

[𝙈𝘼𝙍𝙄𝙉𝘼🦋 @m__sb04]

AI Chip Companies at #CES2021 
・Blaize
・Canaan Creative
・Eta Compute
・GrAI Matter Labs
・Gyrfarcon Technology
・Hailo
・Horizon Robotics
・LeapMind
・XMOS
Check out each exhibitor's booth!
#AIchip #edgeAI #AI #CES

[Denis @tg_bomze]

Face Depixelizer

Given a low-resolution input image, model generates high-resolution images that are perceptually realistic and downscale correctly.

😺GitHub: https://t.co/0WBxkyWkiK
📙Colab: https://t.co/q9SIm4ha5p

P.S. Colab is based on the
https://t.co/fvEvXKvWk2

[Patrick Esser @pess_r]

Pre-tamed transformers now at https://t.co/0vONqf1sYT
Just added a Colab demo to start sampling right away:
https://t.co/c55NnUaLOG

[Jean-Baptiste Lefevre @jblefevre60]

🎖️Big list of Enterprise AI Companies:

#AI #MachineLearning #DeepLearning #DataScience #CES2021

📲https://t.co/thngvZh1Df @topbots @KirkDBorne

@SpirosMargaris @DeepLearn007
@HaroldSinnott @gvalan @ipfconline1 @ShiCooks @diioannid @mvollmer1 @Ym78200 @kalydeoo @Nicochan33

[Nathan Shipley @CitizenPlain]

Another AI #toonify animation test: Uma Thurman + @bellapoarch

Face is made by layer blending FFHQ + toon #StyleGAN models then animated with First Order Motion. Credit for OG code as always to @Norod78 and @Buntworthy!

Source + high res and comparison chart in thread below.

[Made With ML @MadeWithML]

🏆 Today's trending post is ECCV 2020: Some Highlights by @yass_ouali. It's a great way to stay afloat the >1K papers/conference by focusing on general themes (Yassine also released one for this year's CVPR).

ECCV 2020: https://t.co/nuXW5Td5r3

CVPR 2020: https://t.co/N57iMl0qWB