Paper:
https://arxiv.org/pdf/2003.03396.pdf
Github:
https://github.com/happenwah/FVI_CV?fbclid=IwAR2fUnAd8XHEFUiFRCQbLjnl2WUbw8JZVlXNL-zNj7NiIDXWpcMyhoyPIW8
https://arxiv.org/pdf/2003.03396.pdf
Github:
https://github.com/happenwah/FVI_CV?fbclid=IwAR2fUnAd8XHEFUiFRCQbLjnl2WUbw8JZVlXNL-zNj7NiIDXWpcMyhoyPIW8
GitHub
GitHub - happenwah/FVI_CV: Code for Scalable Uncertainty for Computer Vision with Functional Variational Inference @ CVPR 2020
Code for Scalable Uncertainty for Computer Vision with Functional Variational Inference @ CVPR 2020 - happenwah/FVI_CV
π2
This media is not supported in your browser
VIEW IN TELEGRAM
It's CVPR time!
We will not meet in person
next week at CVPR 2020 Seattle:
The conference has gone virtual...
We will not meet in person
next week at CVPR 2020 Seattle:
The conference has gone virtual...
π3
But, You can follow what happens there almost in real time: fill below link and receive every day during CVPR the official magazine CVPR Daily (16-17-18 June) - with all the highlights from CVPR, the Computer Vision and Pattern Recognition conference.
https://www.rsipvision.com/feel-at-cvpr-as-if-you-were-at-cvpr/
Open Access version of papers are available at:
http://openaccess.thecvf.com/CVPR2020.py
https://www.rsipvision.com/feel-at-cvpr-as-if-you-were-at-cvpr/
Open Access version of papers are available at:
http://openaccess.thecvf.com/CVPR2020.py
π2
Recently published Comprehensive survey about role of Deep Learning for Scientific discovery (March, 2020). Well structured information given from the authors by providing supplementary materials (Github code links).
It worth to spend time to read.
It worth to spend time to read.
Tackled the problem of defining a perturbation set for real-world perturbations which cannot be easily described with a set of equations.
Paper: https://arxiv.org/abs/2007.08450
Blog post: https://locuslab.github.io/2020-07-20-perturbation/
Code: https://github.com/locuslab/perturbation_learning
Paper: https://arxiv.org/abs/2007.08450
Blog post: https://locuslab.github.io/2020-07-20-perturbation/
Code: https://github.com/locuslab/perturbation_learning
locuslab.github.io
Learning perturbation sets for robust machine learning
Using generative modeling to capture real-world transformations from data for adversarial robustness
π2
Blog:
https://towardsdatascience.com/pp-yolo-surpasses-yolov4-object-detection-advances-1efc2692aa62
Github:
https://github.com/PaddlePaddle/PaddleDetection
https://towardsdatascience.com/pp-yolo-surpasses-yolov4-object-detection-advances-1efc2692aa62
Github:
https://github.com/PaddlePaddle/PaddleDetection
Medium
PP-YOLO Surpasses YOLOv4 β Object Detection Advances
Baidu publishes PP-YOLO and pushes the state of the art in object detection research by building on top of YOLOv3, the PaddlePaddle deepβ¦
π2
Classification library
https://github.com/Tessellate-Imaging/monk_v1
Notebooks - https://github.com/Tessellate-Imaging/monk_v1/tree/master/study_roadmaps/4_image_classification_zoo
Detection and Segmentation Library
https://github.com/Tessellate-Imaging/
Monk_Object_Detection
Notebooks: https://github.com/Tessellate-Imaging/Monk_Object_Detection/tree/master/application_model_zoo
https://github.com/Tessellate-Imaging/monk_v1
Notebooks - https://github.com/Tessellate-Imaging/monk_v1/tree/master/study_roadmaps/4_image_classification_zoo
Detection and Segmentation Library
https://github.com/Tessellate-Imaging/
Monk_Object_Detection
Notebooks: https://github.com/Tessellate-Imaging/Monk_Object_Detection/tree/master/application_model_zoo
GitHub
GitHub - Tessellate-Imaging/monk_v1: Monk is a low code Deep Learning tool and a unified wrapper for Computer Vision.
Monk is a low code Deep Learning tool and a unified wrapper for Computer Vision. - Tessellate-Imaging/monk_v1
π5