Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/MixMIM-L

MixMIM-L

Reported on 9 benchmarks across 8 tasks · 1 paper · 6 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology4 results

3DonCOCO 2017
mAP· 2022-05-26
54.1
best: 56.4 (UniRepLKNet-XL++)
SOTA
MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers arXiv:2205.13137
2D ClassificationonCOCO 2017
mAP· 2022-05-26
54.1
best: 56.4 (UniRepLKNet-XL++)
SOTA
MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers arXiv:2205.13137
2D Object DetectiononCOCO 2017
mAP· 2022-05-26
54.1
best: 56.4 (UniRepLKNet-XL++)
SOTA
MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers arXiv:2205.13137
16konCOCO 2017
mAP· 2022-05-26
54.1
best: 56.4 (UniRepLKNet-XL++)
SOTA
MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers arXiv:2205.13137

Computer Vision3 results

Object DetectiononCOCO 2017
mAP· 2022-05-26
54.1
best: 56.4 (UniRepLKNet-XL++)
SOTA
MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers arXiv:2205.13137
Image ClassificationonPlaces205
Top 1 Accuracy· 2022-05-26
69.3
SOTA
MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers arXiv:2205.13137
Image ClassificationoniNaturalist 2019
Top-1 Accuracy· 2022-05-26
83.9
best: 88.5 (Hiera-H (448px))
MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers arXiv:2205.13137

Medical1 result

Semantic SegmentationonADE20K val
mIoU· 2022-05-26
53.8
best: 62.8 (BEiT-3)
MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers arXiv:2205.13137

Audio1 result

10-shot image generationonADE20K val
mIoU· 2022-05-26
53.8
best: 62.8 (BEiT-3)
MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers arXiv:2205.13137