Sign inGet started
Repository · GitHub

keyu-tian/SparK

[ICLR'23 Spotlight🔥] The first successful BERT/MAE-style pretraining on any convolutional network; Pytorch impl. of "Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling"

Ownerkeyu-tian
License (as declared)MIT
Stars1,381
Forks85
Main languagePython
Created5 January 2023
Last updated at source23 January 2024
pythonbertcnnconvnetconvolutional-neural-networksdeep-learningiclriclr2023instance-segmentationmaemask-rcnnmasked-autoencodermasked-image-modelingobject-detectionpre-trained-modelpretrainpretrainingpytorchself-supervised-learningsparse-convolutionssl
Embed this entry
<iframe src="https://silytics.si/embed/item/1ffc829c-17fd-4658-826b-1efc6fe3a0f6" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

Silytics shows public metadata from GitHub and links to the original. Information may be incomplete or out of date. Last refreshed 15 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.