
SparK
by keyu-tian (personal account)
[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" (description from the project’s GitHub page)
Repository facts
- Stars
- 1,382
- Forks
- 85
- Open issues and pull requests
- 16
- Primary language
- Python
- License
- MIT License (MIT)
- Owner
- keyu-tian · Personal account
- Created
- Jan 5, 2023
- Last push
- Jan 23, 2024
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 5,919: qqlu/Entity
EntitySeg Toolbox: Towards Open-World and High-Quality Image Segmentation
1,051 starsJupyter NotebookOther licenseLast push Nov 30, 2023
Rank 2,049: open-mmlab/mmpretrain
OpenMMLab Pre-training Toolbox and Benchmark
3,860 starsPythonApache-2.0Last push Nov 1, 2024
Rank 3,977: MCG-NJU/VideoMAE
[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
1,802 starsPythonOther licenseLast push Dec 8, 2023
Rank 2,384: open-mmlab/mmselfsup
OpenMMLab Self-Supervised Learning Toolbox and Benchmark
3,305 starsPythonApache-2.0Last push Jun 25, 2023
Rank 228: open-mmlab/mmdetection
OpenMMLab Detection Toolbox and Benchmark
32,998 starsPythonApache-2.0Last push Aug 21, 2024
Rank 5,849: ayoolaolafenwa/PixelLib
Visit PixelLib's official documentation https://pixellib.readthedocs.io/en/latest/
1,068 starsPythonMITLast push Oct 6, 2023