René's URL Explorer Experiment


Title: ObjectNet

Description: ObjectNet is a large real-world test set for object recognition with control where object backgrounds, rotations, and imaging viewpoints are random. This work opens up new avenues for research in generalizable, robust, and more human-like computer vision and in creating datasets where results are predictive of real-world performance.

Keywords:

Mail addresses
objectnet@mit.edu

direct link

Domain: objectnet.dev

Links:

https://objectnet.dev/index.html
Downloadhttps://objectnet.dev/download.html
Teamhttps://objectnet.dev/team.html
"How hard are computer vision datasets? Calibrating dataset difficulty to viewing time"https://objectnet.dev/mvt/
downloadhttps://objectnet.dev/download.html
Paperhttps://objectnet.dev/objectnet-a-large-scale-bias-controlled-dataset-for-pushing-the-limits-of-object-recognition-models.pdf
Competitionhttps://eval.ai/web/challenges/challenge-page/726/overview
PyTorch codehttps://github.com/abarbu/objectnet-template-pytorch
TensorFlow codehttps://github.com/abarbu/objectnet-template-tensorflow
Downloadhttps://objectnet.dev/download.html
Spoken ObjectNethttps://github.com/iapalm/Spoken-ObjectNet
Image viewing timeshttps://objectnet.dev/flash/index.html

Viewport: width=device-width, initial-scale=.4


URLs of crawlers that visited me.