Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Baseline model in paper #16

Open
bkj opened this issue Nov 8, 2018 · 4 comments
Open

Baseline model in paper #16

bkj opened this issue Nov 8, 2018 · 4 comments

Comments

@bkj
Copy link

bkj commented Nov 8, 2018

Hi -- Have you ever tried to reproduce the baseline results reported in the paper? I implemented Matching Networks from scratch, and my baseline model does substantially better than the one reported in the paper (66% reduction in error). Am asking around to see whether other people have ever noticed a similar issue.

Thanks
Ben

@AntreasAntoniou
Copy link
Owner

AntreasAntoniou commented Nov 8, 2018 via email

@bkj
Copy link
Author

bkj commented Nov 8, 2018

On Omniglot, 5way/1shot and 20way/1shot they report 86.0% and 72.9% accuracies, respectively. I'm getting something like 95% and 90% from the baseline on those tasks.

Note I'm not using the same split as them (I don't think it's available?). This is using the background dataset as training and the evaluation set as testing.

@AntreasAntoniou
Copy link
Owner

AntreasAntoniou commented Nov 8, 2018 via email

@bkj
Copy link
Author

bkj commented Nov 8, 2018

I'm talking about the baseline models, not the Matching Networks.

Model Matching Fn Fine Tune 5-way Acc 20-way Acc
1-shot 5-shot 1-shot 5-shot
PIXELS Cosine N 41.7% 63.2% 26.7% 42.6%
BASELINE CLASSIFIER Cosine N 80.0% 95.0% 69.5% 89.1%
BASELINE CLASSIFIER Cosine Y 82.3% 98.4% 70.6% 92.0%
BASELINE CLASSIFIER Softmax Y 86.0% 97.6% 72.9% 92.3% ***
MANN (NO CONV) [21] Cosine N 82.8% 94.9% – –
CONVOLUTIONAL SIAMESE NET [11] Cosine N 96.7% 98.4% 88.0% 96.5%
CONVOLUTIONAL SIAMESE NET [11] Cosine Y 97.3% 98.4% 88.1% 97.0%
MATCHING NETS (OURS) Cosine N 98.1% 98.9% 93.8% 98.5%
MATCHING NETS (OURS) Cosine Y 97.9% 98.7% 93.5% 98.7%

I'm talking about the ***

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants