Search
morrislee
Apr 5, 20211 min read
Transformers improve feature matching in images
Transformers improve feature matching in images LoFTR: Detector-Free Local Feature Matching with Transformers arXiv paper abstract...
28 views0 comments
morrislee
Apr 2, 20211 min read
Labeling TV video with Google reverse image search
Labeling TV video with Google reverse image search Using Google Vision AI's Reverse Image Search To Richly Catalog Television News Forbes...
25 views0 comments
morrislee
Apr 1, 20211 min read
DCVNet for improved optical flow pixel tracking in video
DCVNet for improved optical flow pixel tracking in video DCVNet: Dilated Cost Volume Networks for Fast Optical Flow arXiv paper abstract...
9 views0 comments
morrislee
Mar 31, 20211 min read
Facebook AI's MADGRAD optimizer improves neural network training
Facebook AI's MADGRAD optimizer improves neural network training Adaptivity without Compromise: A Momentumized, Adaptive, Dual Averaged...
34 views0 comments
morrislee
Mar 30, 20211 min read
Turn Your ConvNet into a Zero-Shot Learner
Turn Your ConvNet into a Zero-Shot Learner Classifier Crafting: Turn Your ConvNet into a Zero-Shot Learner! DeepAI...
17 views0 comments
morrislee
Mar 29, 20211 min read
Fast interactive video segmentation to replace tedious pixel labeling of video
Fast interactive video segmentation to replace tedious pixel labeling of video Fast Interactive Video Object Segmentation with Graph...
7 views0 comments
morrislee
Mar 26, 20211 min read
Training Computer Vision Transformers without Natural Images
Can Vision Transformers Learn without Natural Images? Deep AI https://deepai.org/publication/can-vision-transformers-learn-without-natura...
20 views0 comments
morrislee
Mar 25, 20211 min read
Google Reinforcement Learning uses successful examples instead of tricky reward functions
Google Reinforcement Learning uses successful examples instead of tricky reward functions Google AI blog https://ai.googleblog.com/2021/0...
16 views0 comments
morrislee
Mar 24, 20211 min read
Google's MoViNets: Mobile Video Networks for Efficient Video Recognition
Google's MoViNets: Mobile Video Networks for Efficient Video Recognition arXiv abstract https://arxiv.org/abs/2103.11511v1 . . . 3D...
29 views0 comments
morrislee
Mar 24, 20211 min read
Tiny four-bit computers may enable neural nets to be trained directly on smartphones
Tiny four-bit computers may enable neural nets to be trained directly on smartphones M.I.T. Technology Review https://www.technologyrevie...
54 views0 comments
morrislee
Mar 23, 20211 min read
PyTorch implementation of Yann LeCun Barlow Twins: Self-Supervised Learning via Redundancy Reduction
PyTorch implementation of Yann LeCun "Barlow Twins: Self-Supervised Learning via Redundancy Reduction" Synced article...
50 views0 comments
morrislee
Mar 18, 20211 min read
Use PixelLib to extract objects in images and videos with 5 lines of code
Use PixelLib to extract objects in images and videos with 5 Lines of code For example, first do the following: pip3 install pixellib Then...
115 views0 comments
morrislee
Mar 15, 20211 min read
Use PyCaret to apply 14 ML models at once and explore data
Use PyCaret to apply 14 machine learning models at once with only 5 lines of Python code. PyCaret can also be used to explore data. For...
68 views0 comments
morrislee
Mar 14, 20211 min read
Top 10 Computer Vision Papers in 2020
Top 10 Computer Vision Papers in 2020 KDnuggets article https://www.kdnuggets.com/2021/01/top-10-computer-vision-papers-2020.html The top...
16 views0 comments
morrislee
Feb 24, 20211 min read
GPT-3 AI can write a passing college paper in 20 minutes
GPT-3 AI can write a passing college paper in 20 minutes ZDNet article https://www.zdnet.com/article/ai-can-write-a-passing-college-paper...
151 views0 comments
morrislee
Feb 21, 20211 min read
Georgia Tech and Facebook Reduce Size of Deep Learning Recommendation Models by Factor of 112
Georgia Tech and Facebook AI Researchers Devise a New Tensor Train Approach to Reduce the Size of Deep Learning Recommendation Models up...
18 views0 comments
morrislee
Feb 19, 20211 min read
Google Model Search AutoML automatically optimizes and identifies AI models
Google Model Search AutoML automatically optimizes and identifies AI models VentureBeat article https://venturebeat.com/2021/02/19/google...
30 views0 comments
morrislee
Feb 17, 20211 min read
Google trained a trillion-parameter AI language model
Google trained a trillion-parameter AI language model VentureBeat article https://venturebeat.com/2021/01/12/google-trained-a-trillion-pa...
37 views0 comments
morrislee
Feb 14, 20211 min read
Machine learning with less than one example per class
Machine learning with less than one example per class TechTalks article https://bdtechtalks.com/2020/10/01/less-than-one-shot-machine-lea...
54 views0 comments
morrislee
Feb 10, 20211 min read
New Kaggle survey on ML and Data Science
Kaggle releases survey on Machine Learning and Data Science InfoQ article https://www.infoq.com/news/2021/02/kaggle-report-2020 Kaggle...
89 views0 comments