pytorch-metric-learning

pytorch-metric-learning copied to clipboard

utils.inference: make default match_finder and knn_func use same distance metric

1

Also it might be possible to replace the functionality of ```match_finder``` with ```knn_func```

KevinMusgrave

Add versioned documentation

2

See: https://github.com/jimporter/mike. This makes mkdocs support versioned docs.

KevinMusgrave

Add wrapper for self supervised loss

2

A common use case is to have ```embeddings``` and ```ref_emb``` be augmented versions of each other. For most losses right now you have to create labels to indicate which ```embeddings```...

KevinMusgrave

add smoothap

1

add smoothap loss (ECCV2020)

interestingzhuo

Manifold similarity loss

1

Would you please repoduce the manifold similarity loss proposed in > thanks a lot!

Kingofolk

https://arxiv.org/pdf/2110.06848.pdf

aleSuglia

Add nearest-centroid accuracy as a default metric for AccuracyCalculator

1

- Compute centroid of each class in the reference set - Find nearest centroid for each query embedding. It gets a score of 1 if the nearest centroid is the...

KevinMusgrave

Spherical Embedding Constraint (SEC)

2

Do you plan to add the Spherical Embedding Constraint (SEC) proposed in the following paper? (https://arxiv.org/pdf/2011.02785.pdf)

StefanoSalvatori

Hierarchical Triplet Loss

8

Hey! Any objections adding Hierarchical Triplet Loss (HTL), described [here](https://arxiv.org/pdf/1810.06951)? Happy to work on a Pull Request.

kachayev

Basically something like sklearn KNeighborsClassifier. We could also add nearest-centroid classification and others. See #342 and #343

KevinMusgrave