Loading
0 Follower
0 Following
mseitzer

Location

DE

Badges

1
1
0

Activity

Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
Dec
Jan
Feb
Mar
Mon
Wed
Fri

Ratings Progression

Loading...

Challenge Categories

Loading...

Challenges Entered

Latest submissions

No submissions made in this challenge.

Latest submissions

See All
graded 21042
graded 21037
graded 21033

Robots that learn to interact with the environment autonomously

Latest submissions

See All
failed 21943
failed 21942
failed 21938
Participant Rating
Participant Rating

NeurIPS 2019 : Disentanglement Challenge

Use of labels of published datasets

Over 4 years ago

Hi,

is it allowed to use the labels (i.e. ground truth factors) of the published datasets (mpi3d_toy and mpi3d_realistic) in any way for pretraining?

In [Announcement] Regarding Transfer Learning!, you stated that it is allowed to use any data to produce pretrained weights. Following this wording, using the labels is allowed.

Can you confirm this please?

Topic withdrawn

Over 4 years ago

(topic withdrawn by author, will be automatically deleted in 24 hours unless flagged)

Which tag in git will you choose for final ranking?

Over 4 years ago

Can you clarify this further please? What exactly is the rank? Does the best score on a metric get rank 1, second best score gets rank 2, etc?

Furthermore, do you average over all submissions, or do you just take the submission with the best scores into account?

mseitzer has not provided any information yet.