metadata
license: mit
datasets:
- imagenet-1k
metrics:
- accuracy
pipeline_tag: image-classification
mrl-convnext-tiny
We provide a ConvNeXt-Tiny model trained with Matryoshka Representation Learning (MRL) from scratch on ImageNet-1K, adapted from the original repository. We train with a Matryoshka Loss at [d] = {48, 96, 192, 384, 786},
Top-1 Retrieval Accuracy (1-nearest neighbor) of mrl-convnext-tiny on ImageNet-1K with Exact search and IVF search across vector dimensionality.