Note
You are reading the documentation for MMSelfSup 0.x, which will soon be deprecated by the end of 2022. We recommend you upgrade to MMSelfSup 1.0.0rc versions to enjoy fruitful new features and better performance brought by OpenMMLab 2.0. Check out the changelog, code and documentation of MMSelfSup 1.0.0rc for more details.
Model Zoo¶
All models and part of benchmark results are recorded below.
Pre-trained models¶
Remarks:
The training details are recorded in the config names.
You can click algorithm name to obtain more information.
Benchmarks¶
In the following tables, we only display ImageNet linear evaluation, ImageNet fine-tuning, COCO17 object detection and instance segmentation, and PASCAL VOC12 Aug semantic segmentation. You can click algorithm name above to check more comprehensive benchmark results.
ImageNet Linear Evaluation¶
If not specified, we use linear evaluation setting from MoCo as default. Other settings are mentioned in Remarks.
ImageNet Fine-tuning¶
Algorithm | Config | Remarks | Top-1 (%) |
---|---|---|---|
MAE | mae_vit-base-p16_8xb512-coslr-400e_in1k | 83.1 | |
SimMIM | simmim_swin-base_16xb128-coslr-100e_in1k-192 | 82.9 | |
CAE | cae_vit-base-p16_8xb256-fp16-coslr-300e_in1k | 83.2 | |
MaskFeat | maskfeat_vit-base-p16_8xb256-fp16-coslr-300e_in1k | 83.5 |
COCO17 Object Detection and Instance Segmentation¶
In COCO17 object detection and instance segmentation task, we choose the evaluation protocol from MoCo, with Mask-RCNN FPN architecture. The results below are fine-tuned with the same config.
Algorithm | Config | mAP (Box) | mAP (Mask) |
---|---|---|---|
Relative Location | relative-loc_resnet50_8xb64-steplr-70e_in1k | 37.5 | 33.7 |
Rotation Prediction | rotation-pred_resnet50_8xb16-steplr-70e_in1k | 37.9 | 34.2 |
NPID | npid_resnet50_8xb32-steplr-200e_in1k | 38.5 | 34.6 |
SimCLR | simclr_resnet50_8xb32-coslr-200e_in1k | 38.7 | 34.9 |
MoCo v2 | mocov2_resnet50_8xb32-coslr-200e_in1k | 40.2 | 36.1 |
BYOL | byol_resnet50_8xb32-accum16-coslr-200e_in1k | 40.9 | 36.8 |
SwAV | swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96 | 40.2 | 36.3 |
SimSiam | simsiam_resnet50_8xb32-coslr-100e_in1k | 38.6 | 34.6 |
simsiam_resnet50_8xb32-coslr-200e_in1k | 38.8 | 34.9 |
Pascal VOC12 Aug Semantic Segmentation¶
In Pascal VOC12 Aug semantic segmentation task, we choose the evaluation protocol from MMSeg, with FCN architecture. The results below are fine-tuned with the same config.
Algorithm | Config | mIOU |
---|---|---|
Relative Location | relative-loc_resnet50_8xb64-steplr-70e_in1k | 63.49 |
Rotation Prediction | rotation-pred_resnet50_8xb16-steplr-70e_in1k | 64.31 |
NPID | npid_resnet50_8xb32-steplr-200e_in1k | 65.45 |
SimCLR | simclr_resnet50_8xb32-coslr-200e_in1k | 64.03 |
MoCo v2 | mocov2_resnet50_8xb32-coslr-200e_in1k | 67.55 |
BYOL | byol_resnet50_8xb32-accum16-coslr-200e_in1k | 67.16 |
SwAV | swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96 | 63.73 |
DenseCL | densecl_resnet50_8xb32-coslr-200e_in1k | 69.47 |
SimSiam | simsiam_resnet50_8xb32-coslr-100e_in1k | 48.35 |
simsiam_resnet50_8xb32-coslr-200e_in1k | 46.27 |