Shortcuts

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

Algorithm Config Download
Relative Location relative-loc_resnet50_8xb64-steplr-70e_in1k model | log
Rotation Prediction rotation-pred_resnet50_8xb16-steplr-70e_in1k model | log
DeepCluster deepcluster-sobel_resnet50_8xb64-steplr-200e_in1k model
NPID npid_resnet50_8xb32-steplr-200e_in1k model | log
ODC odc_resnet50_8xb64-steplr-440e_in1k model | log
SimCLR simclr_resnet50_8xb32-coslr-200e_in1k model | log
simclr_resnet50_16xb256-coslr-200e_in1k model | log
MoCo v2 mocov2_resnet50_8xb32-coslr-200e_in1k model | log
BYOL byol_resnet50_8xb32-accum16-coslr-200e_in1k model | log
byol_resnet50_16xb256-coslr-200e_in1k model | log
byol_resnet50_8xb32-accum16-coslr-300e_in1k model | log
SwAV swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96 model | log
DenseCL densecl_resnet50_8xb32-coslr-200e_in1k model | log
SimSiam simsiam_resnet50_8xb32-coslr-100e_in1k model | log
simsiam_resnet50_8xb32-coslr-200e_in1k model | log
BarlowTwins barlowtwins_resnet50_8xb256-coslr-300e_in1k model | log
MoCo v3 mocov3_vit-small-p16_32xb128-fp16-coslr-300e_in1k-224 model | log
InterCLR interclr-moco_resnet50_8xb32-coslr-200e_in1k model | log
MAE mae_vit-base-p16_8xb512-coslr-400e_in1k model | log
SimMIM simmim_swin-base_16xb128-coslr-100e_in1k-192 model | log
CAE cae_vit-base-p16_8xb256-fp16-coslr-300e_in1k model | log
MaskFeat maskfeat_vit-base-p16_8xb256-coslr-300e_in1k model | log

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.

Algorithm Config Remarks Top-1 (%)
Relative Location relative-loc_resnet50_8xb64-steplr-70e_in1k 38.78
Rotation Prediction rotation-pred_resnet50_8xb16-steplr-70e_in1k 48.12
DeepCluster deepcluster-sobel_resnet50_8xb64-steplr-200e_in1k.py 46.92
NPID npid_resnet50_8xb32-steplr-200e_in1k 58.97
ODC odc_resnet50_8xb64-steplr-440e_in1k 53.43
SimCLR simclr_resnet50_8xb32-coslr-200e_in1k SimSiam paper setting 62.56
simclr_resnet50_16xb256-coslr-200e_in1k SimSiam paper setting 66.66
MoCo v2 mocov2_resnet50_8xb32-coslr-200e_in1k 67.58
BYOL byol_resnet50_8xb32-accum16-coslr-200e_in1k SimSiam paper setting 71.72
byol_resnet50_16xb256-coslr-200e_in1k SimSiam paper setting 71.88
byol_resnet50_8xb32-accum16-coslr-300e_in1k SimSiam paper setting 72.93
SwAV swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96 SwAV paper setting 70.47
DenseCL densecl_resnet50_8xb32-coslr-200e_in1k 63.62
SimSiam simsiam_resnet50_8xb32-coslr-100e_in1k SimSiam paper setting 68.28
simsiam_resnet50_8xb32-coslr-200e_in1k SimSiam paper setting 69.84
Barlow Twins barlowtwins_resnet50_8xb256-coslr-300e_in1k Barlow Twins paper setting 71.66
MoCo v3 mocov3_vit-small-p16_32xb128-fp16-coslr-300e_in1k-224 MoCo v3 paper setting 73.19
InterCLR interclr-moco_resnet50_8xb32-coslr-200e_in1k 68.04

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
Read the Docs v: dev
Versions
latest
stable
1.x
dev-1.x
dev
Downloads
pdf
html
epub
On Read the Docs
Project Home
Builds

Free document hosting provided by Read the Docs.