mirrors
/
mmselfsup
mirror of https://github.com/open-mmlab/mmselfsup.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[Docs] update benchmark results (#17) 

* [Docs] add partial results

* [Docs] update results
pull/133/head
Jiahao Xie 2021-12-16 11:32:04 +08:00 committed by GitHub
parent 3380dce973
commit 6320bba34a
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
12 changed files with 24 additions and 98 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
configs/selfsup/byol/README.md
View File

@ -72,7 +72,7 @@ Please refer to [mask_rcnn_r50_fpn_mstrain_1x_coco.py](../../benchmarks/mmdetect
| Self-Supervised Config | mAP(Box) | AP50(Box) | AP75(Box) | mAP(Mask) | AP50(Mask) | AP75(Mask) |
| ----------------------------------------------------------------------------------- | -------- | --------- | --------- | --------- | ---------- | ---------- |
| [resnet50_8xb32-accum16-coslr-200e](byol_resnet50_8xb32-accum16-coslr-200e_in1k.py) | | | | | | |
| [resnet50_8xb32-accum16-coslr-200e](byol_resnet50_8xb32-accum16-coslr-200e_in1k.py) | 40.9 | 61.0 | 44.6 | 36.8 | 58.1 | 39.5 |
### Segmentation

32
configs/selfsup/deepcluster/README.md
View File

@ -53,35 +53,3 @@ The **AvgPool** result is obtained from Linear Evaluation with GlobalAveragePool
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 | AvgPool |
| ---------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- | ------- |
| [sobel_resnet50_8xb64-steplr-200e](deepcluster-sobel_resnet50_8xb64-steplr-200e_in1k.py) | 12.78 | 30.81 | 43.88 | 57.71 | 51.68 | 46.92 |
### Detection
The detection benchmarks includes 2 downstream task datasets, **Pascal VOC 2007 + 2012** and **COCO2017**. This benchmark follows the evluation protocols set up by MoCo.
#### Pascal VOC 2007 + 2012
Please refer to [faster_rcnn_r50_c4_mstrain_24k_voc0712.py](../../benchmarks/mmdetection/voc0712/faster_rcnn_r50_c4_mstrain_24k_voc0712.py) for details of config.
| Self-Supervised Config | AP50 |
| ---------------------------------------------------------------------------------------- | ---- |
| [sobel_resnet50_8xb64-steplr-200e](deepcluster-sobel_resnet50_8xb64-steplr-200e_in1k.py) | | |
#### COCO2017
Please refer to [mask_rcnn_r50_fpn_mstrain_1x_coco.py](../../benchmarks/mmdetection/coco/mask_rcnn_r50_fpn_mstrain_1x_coco.py) for details of config.
| Self-Supervised Config | mAP(Box) | AP50(Box) | AP75(Box) | mAP(Mask) | AP50(Mask) | AP75(Mask) |
| ---------------------------------------------------------------------------------------- | -------- | --------- | --------- | --------- | ---------- | ---------- |
| [sobel_resnet50_8xb64-steplr-200e](deepcluster-sobel_resnet50_8xb64-steplr-200e_in1k.py) | | | | | | |
### Segmentation
The segmentation benchmarks includes 2 downstream task datasets, **Cityscapes** and **Pascal VOC 2012 + Aug**. It follows the evluation protocols set up by MMSegmentation.
#### Pascal VOC 2012 + Aug
Please refer to [fcn_r50-d8_512x512_20k_voc12aug.py](../../benchmarks/mmsegmentation/voc12aug/fcn_r50-d8_512x512_20k_voc12aug.py) for details of config.
| Self-Supervised Config | mIOU |
| ---------------------------------------------------------------------------------------- | ----- |
| [sobel_resnet50_8xb64-steplr-200e](deepcluster-sobel_resnet50_8xb64-steplr-200e_in1k.py) | 59.69 |

4
configs/selfsup/densecl/README.md
View File

@ -42,7 +42,7 @@ Besides, k=1 to 96 indicates the hyper-parameter of Low-shot SVM.
| Self-Supervised Config | Best Layer | SVM | k=1 | k=2 | k=4 | k=8 | k=16 | k=32 | k=64 | k=96 |
| ---------------------------------------------------------------------- | ---------- | --- | --- | --- | --- | --- | ---- | ---- | ---- | ---- |
| [resnet50_8xb32-coslr-200e](densecl_resnet50_8xb32-coslr-200e_in1k.py) | | | | | | | | | | |
| [resnet50_8xb32-coslr-200e](densecl_resnet50_8xb32-coslr-200e_in1k.py) | feature5 |82.5|42.68|50.64|61.74|68.17|72.99|76.07|79.19|80.55|
#### ImageNet Linear Evaluation
@ -52,7 +52,7 @@ The **AvgPool** result is obtained from Linear Evaluation with GlobalAveragePool
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 | AvgPool |
| ---------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- | ------- |
| [resnet50_8xb32-coslr-200e](densecl_resnet50_8xb32-coslr-200e_in1k.py) | | | | | | |
| [resnet50_8xb32-coslr-200e](densecl_resnet50_8xb32-coslr-200e_in1k.py) | 15.86 | 35.47 | 49.46 | 64.06 | 62.95 | 63.34 |
### Detection

2
configs/selfsup/moco/README.md
View File

@ -96,7 +96,7 @@ Please refer to [mask_rcnn_r50_fpn_mstrain_1x_coco.py](../../benchmarks/mmdetect
| Self-Supervised Config | mAP(Box) | AP50(Box) | AP75(Box) | mAP(Mask) | AP50(Mask) | AP75(Mask) |
| ---------------------------------------------------------------------------- | -------- | --------- | --------- | --------- | ---------- | ---------- |
| [mocov2_resnet50_8xb32-coslr-200e](mocov2_resnet50_8xb32-coslr-200e_in1k.py) | | | | | | |
| [mocov2_resnet50_8xb32-coslr-200e](mocov2_resnet50_8xb32-coslr-200e_in1k.py) | 40.2 | 59.7 | 44.2 | 36.1 | 56.7 | 38.8 |
### Segmentation

8
configs/selfsup/npid/README.md
View File

@ -47,7 +47,6 @@ Besides, k=1 to 96 indicates the hyper-parameter of Low-shot SVM.
| Self-Supervised Config | Best Layer | SVM | k=1 | k=2 | k=4 | k=8 | k=16 | k=32 | k=64 | k=96 |
| ------------------------------------------------------------------------------------------- | ---------- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- |
| [resnet50_8xb32-steplr-200e](npid_resnet50_8xb32-steplr-200e_in1k.py) | feature5 | 76.75 | 26.96 | 35.37 | 44.48 | 53.89 | 60.39 | 66.41 | 71.48 | 73.39 |
| [ensure-neg_resnet50_8xb32-steplr-200e](npid-ensure-neg_resnet50_8xb32-steplr-200e_in1k.py) | feature5 | 76.59 | 27.22 | 34.73 | 44.30 | 53.82 | 59.97 | 66.11 | 71.27 | 73.12 |
#### ImageNet Linear Evaluation
@ -57,7 +56,7 @@ The **AvgPool** result is obtained from Linear Evaluation with GlobalAveragePool
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 | AvgPool |
| --------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- | ------- |
| [resnet50_8xb32-steplr-200e](npid_resnet50_8xb32-steplr-200e_in1k.py) | | | | | | |
| [resnet50_8xb32-steplr-200e](npid_resnet50_8xb32-steplr-200e_in1k.py) | 14.68 | 31.98 | 42.85 | 56.95 | 58.41 | 58.16 |
### Detection
@ -69,9 +68,7 @@ Please refer to [faster_rcnn_r50_c4_mstrain_24k_voc0712.py](../../benchmarks/mmd
| Self-Supervised Config | AP50 |
| ------------------------------------------------------------------------------------------- | ---- |
| [resnet50_8xb32-steplr-200e](npid_resnet50_8xb32-steplr-200e_in1k.py) | |
| [ensure-neg_resnet50_8xb32-steplr-200e](npid-ensure-neg_resnet50_8xb32-steplr-200e_in1k.py) | |
| [resnet50_8xb32-steplr-200e](npid_resnet50_8xb32-steplr-200e_in1k.py) |79.52 |
#### COCO2017
@ -92,4 +89,3 @@ Please refer to [fcn_r50-d8_512x512_20k_voc12aug.py](../../benchmarks/mmsegmenta
| Self-Supervised Config | mIOU |
| ------------------------------------------------------------------------------------------- | ----- |
| [resnet50_8xb32-steplr-200e](npid_resnet50_8xb32-steplr-200e_in1k.py) | 65.45 |
| [ensure-neg_resnet50_8xb32-steplr-200e](npid-ensure-neg_resnet50_8xb32-steplr-200e_in1k.py) | 64.73 |

32
configs/selfsup/odc/README.md
View File

@ -53,35 +53,3 @@ The **AvgPool** result is obtained from Linear Evaluation with GlobalAveragePool
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 | AvgPool |
| -------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- | ------- |
| [resnet50_8xb64-steplr-440e](odc_resnet50_8xb64-steplr-440e_in1k.py) | 14.76 | 31.82 | 42.44 | 55.76 | 57.70 | 53.42 |
### Detection
The detection benchmarks includes 2 downstream task datasets, **Pascal VOC 2007 + 2012** and **COCO2017**. This benchmark follows the evluation protocols set up by MoCo.
#### Pascal VOC 2007 + 2012
Please refer to [faster_rcnn_r50_c4_mstrain_24k_voc0712.py](../../benchmarks/mmdetection/voc0712/faster_rcnn_r50_c4_mstrain_24k_voc0712.py) for details of config.
| Self-Supervised Config | AP50 |
| -------------------------------------------------------------------- | ---- |
| [resnet50_8xb64-steplr-440e](odc_resnet50_8xb64-steplr-440e_in1k.py) | |
#### COCO2017
Please refer to [mask_rcnn_r50_fpn_mstrain_1x_coco.py](../../benchmarks/mmdetection/coco/mask_rcnn_r50_fpn_mstrain_1x_coco.py) for details of config.
| Self-Supervised Config | mAP(Box) | AP50(Box) | AP75(Box) | mAP(Mask) | AP50(Mask) | AP75(Mask) |
| -------------------------------------------------------------------- | -------- | --------- | --------- | --------- | ---------- | ---------- |
| [resnet50_8xb64-steplr-440e](odc_resnet50_8xb64-steplr-440e_in1k.py) | | | | | | |
### Segmentation
The segmentation benchmarks includes 2 downstream task datasets, **Cityscapes** and **Pascal VOC 2012 + Aug**. It follows the evluation protocols set up by MMSegmentation.
#### Pascal VOC 2012 + Aug
Please refer to [fcn_r50-d8_512x512_20k_voc12aug.py](../../benchmarks/mmsegmentation/voc12aug/fcn_r50-d8_512x512_20k_voc12aug.py) for details of config.
| Self-Supervised Config | mIOU |
| -------------------------------------------------------------------- | ----- |
| [resnet50_8xb64-steplr-440e](odc_resnet50_8xb64-steplr-440e_in1k.py) | 54.76 |

4
configs/selfsup/relative_loc/README.md
View File

@ -64,7 +64,7 @@ Please refer to [faster_rcnn_r50_c4_mstrain_24k_voc0712.py](../../benchmarks/mmd
| Self-Supervised Config | AP50 |
| --------------------------------------------------------------------------- | ---- |
| [resnet50_8xb64-steplr-70e](relative-loc_resnet50_8xb64-steplr-70e_in1k.py) | |
| [resnet50_8xb64-steplr-70e](relative-loc_resnet50_8xb64-steplr-70e_in1k.py) | 79.70 |
#### COCO2017
@ -72,7 +72,7 @@ Please refer to [mask_rcnn_r50_fpn_mstrain_1x_coco.py](../../benchmarks/mmdetect
| Self-Supervised Config | mAP(Box) | AP50(Box) | AP75(Box) | mAP(Mask) | AP50(Mask) | AP75(Mask) |
| --------------------------------------------------------------------------- | -------- | --------- | --------- | --------- | ---------- | ---------- |
| [resnet50_8xb64-steplr-70e](relative-loc_resnet50_8xb64-steplr-70e_in1k.py) | | | | | | |
| [resnet50_8xb64-steplr-70e](relative-loc_resnet50_8xb64-steplr-70e_in1k.py) | 37.5 | 56.2 | 41.3 | 33.7 | 53.3 | 36.1 |
### Segmentation

2
configs/selfsup/rotation_pred/README.md
View File

@ -72,7 +72,7 @@ Please refer to [mask_rcnn_r50_fpn_mstrain_1x_coco.py](../../benchmarks/mmdetect
| Self-Supervised Config | mAP(Box) | AP50(Box) | AP75(Box) | mAP(Mask) | AP50(Mask) | AP75(Mask) |
| ---------------------------------------------------------------------------- | -------- | --------- | --------- | --------- | ---------- | ---------- |
| [resnet50_8xb16-steplr-70e](rotation-pred_resnet50_8xb16-steplr-70e_in1k.py) | | | | | | |
| [resnet50_8xb16-steplr-70e](rotation-pred_resnet50_8xb16-steplr-70e_in1k.py) | 37.9 | 56.5 | 41.5 | 34.2 | 53.9 | 36.7 |
### Segmentation

2
configs/selfsup/simclr/README.md
View File

@ -72,7 +72,7 @@ Please refer to [mask_rcnn_r50_fpn_mstrain_1x_coco.py](../../benchmarks/mmdetect
| Self-Supervised Config | mAP(Box) | AP50(Box) | AP75(Box) | mAP(Mask) | AP50(Mask) | AP75(Mask) |
| --------------------------------------------------------------------- | -------- | --------- | --------- | --------- | ---------- | ---------- |
| [resnet50_8xb32-coslr-200e](simclr_resnet50_8xb32-coslr-200e_in1k.py) | | | | | | |
| [resnet50_8xb32-coslr-200e](simclr_resnet50_8xb32-coslr-200e_in1k.py) | 38.7 | 58.1 | 42.4 | 34.9 | 55.3 | 37.5 |
### Segmentation

4
configs/selfsup/simsiam/README.md
View File

@ -76,8 +76,8 @@ Please refer to [mask_rcnn_r50_fpn_mstrain_1x_coco.py](../../benchmarks/mmdetect
| Self-Supervised Config | mAP(Box) | AP50(Box) | AP75(Box) | mAP(Mask) | AP50(Mask) | AP75(Mask) |
| ---------------------------------------------------------------------- | -------- | --------- | --------- | --------- | ---------- | ---------- |
| [resnet50_8xb32-coslr-100e](simsiam_resnet50_8xb32-coslr-100e_in1k.py) | | | | | | |
| [resnet50_8xb32-coslr-200e](simsiam_resnet50_8xb32-coslr-200e_in1k.py) | | | | | | |
| [resnet50_8xb32-coslr-100e](simsiam_resnet50_8xb32-coslr-100e_in1k.py) | 38.3 | 57.6 | 41.7 | 34.4 | 54.8 | 36.9 |
| [resnet50_8xb32-coslr-200e](simsiam_resnet50_8xb32-coslr-200e_in1k.py) | 38.8 | 58.0 | 42.3 | 34.9 | 55.3 | 37.6 |
### Segmentation

2
configs/selfsup/swav/README.md
View File

@ -72,7 +72,7 @@ Please refer to [mask_rcnn_r50_fpn_mstrain_1x_coco.py](../../benchmarks/mmdetect
| Self-Supervised Config | mAP(Box) | AP50(Box) | AP75(Box) | mAP(Mask) | AP50(Mask) | AP75(Mask) |
| ---------------------------------------------------------------------------------------------------------- | -------- | --------- | --------- | --------- | ---------- | ---------- |
| [resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96](swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96.py) | | | | | | |
| [resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96](swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96.py) | 40.2 | 60.5 | 43.9 | 36.3 | 57.5 | 38.8 |
### Segmentation

28
docs/model_zoo.md
View File

@ -12,8 +12,7 @@ All models and benchmarks results are recorded below.
| [DenseCL](../configs/selfsup/densecl/README.md) | [densecl_resnet50_8xb32-coslr-200e_in1k](../configs/selfsup/densecl/densecl_resnet50_8xb32-coslr-200e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/densecl/densecl_resnet50_8xb32-coslr-200e_in1k_20211214-1efb342c.pth) |
| [MoCo v2](../configs/selfsup/moco/README.md) | [mocov2_resnet50_8xb32-coslr-200e_in1k](../configs/selfsup/moco/mocov2_resnet50_8xb32-coslr-200e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/moco/mocov2_resnet50_8xb32-coslr-200e_in1k_20211213-7ce8f840.pth) |
| [NPID](../configs/selfsup/npid/README.md) | [npid_resnet50_8xb32-steplr-200e_in1k](../configs/selfsup/npid/npid_resnet50_8xb32-steplr-200e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/npid/npid_resnet50_8xb32-steplr-200e_in1k_20211213-b5fec6df.pth) |
| | [npid-ensure-neg_resnet50_8xb32-steplr-200e_in1k](../configs/selfsup/npid/npid-ensure-neg_resnet50_8xb32-steplr-200e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/npid/npid-ensure-neg_resnet50_8xb32-steplr-200e_in1k_20211213-1052e779.pth) |
| [Online DeepCluster](../configs/selfsup/odc/README.md) | [odc_resnet50_8xb64-steplr-440e_in1k](../configs/selfsup/odc/odc_resnet50_8xb64-steplr-440e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/odc/odc_resnet50_8xb64-steplr-440e_in1k-5af5dd0c.pth) |
| [ODC](../configs/selfsup/odc/README.md) | [odc_resnet50_8xb64-steplr-440e_in1k](../configs/selfsup/odc/odc_resnet50_8xb64-steplr-440e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/odc/odc_resnet50_8xb64-steplr-440e_in1k-5af5dd0c.pth) |
| [Relative Location](../configs/selfsup/relative_loc/README.md) | [relative-loc_resnet50_8xb64-steplr-70e_in1k](../configs/selfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k_20211213-cdd3162f.pth) |
| [Rotation Prediction](../configs/selfsup/rotation_pred/README.md) | [rotation-pred_resnet50_8xb16-steplr-70e_in1k](../configs/selfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k_20211213-513972ac.pth) |
| [SimCLR](../configs/selfsup/simclr/README.md) | [simclr_resnet50_8xb32-coslr-200e_in1k](../configs/selfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k_20211213-d0e53669.pth) |
@ -36,10 +35,9 @@ If not specified, we use linear evaluation setting from [MoCo](http://openaccess
| ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------- | --------------------- | --------- |
| BYOL | [byol_resnet50_8xb32-accum16-coslr-200e_in1k](../configs/selfsup/byol/byol_resnet50_8xb32-accum16-coslr-200e_in1k.py) | | 67.68 |
| DeepCLuster | [deepcluster-sobel_resnet50_8xb64-steplr-200e_in1k.py](../configs/selfsup/deepcluster/deepcluster-sobel_resnet50_8xb64-steplr-200e_in1k.py) | | 46.92 |
| DenseCL | [densecl_resnet50_8xb32-coslr-200e_in1k](../configs/selfsup/densecl/densecl_resnet50_8xb32-coslr-200e_in1k.py) | | |
| DenseCL | [densecl_resnet50_8xb32-coslr-200e_in1k](../configs/selfsup/densecl/densecl_resnet50_8xb32-coslr-200e_in1k.py) | | 63.34 |
| MoCo v2 | [mocov2_resnet50_8xb32-coslr-200e_in1k](../configs/selfsup/moco/mocov2_resnet50_8xb32-coslr-200e_in1k.py) | | 67.56 |
| NPID | [npid_resnet50_8xb32-steplr-200e_in1k](../configs/selfsup/npid/npid_resnet50_8xb32-steplr-200e_in1k.py) | | |
| | [npid-ensure-neg_resnet50_8xb32-steplr-200e_in1k](../configs/selfsup/npid/npid-ensure-neg_resnet50_8xb32-steplr-200e_in1k.py) | | |
| NPID | [npid_resnet50_8xb32-steplr-200e_in1k](../configs/selfsup/npid/npid_resnet50_8xb32-steplr-200e_in1k.py) | | 58.16 |
| ODC | [odc_resnet50_8xb64-steplr-440e_in1k](../configs/selfsup/odc/odc_resnet50_8xb64-steplr-440e_in1k.py) | | 53.42 |
| Relative Location | [relative-loc_resnet50_8xb64-steplr-70e_in1k](../configs/selfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k.py) | | 39.65 |
| Rotation Prediction | [rotation-pred_resnet50_8xb16-steplr-70e_in1k](../configs/selfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k.py) | | 44.35 |
@ -54,19 +52,16 @@ In COCO17 Object detection task, we choose the evluation protocol from [MoCo](ht
| Algorithm | Config | mAP (Box) | mAP (Mask) |
| ------------------- | ---------------------------------------------------------------------------------------------------------------------------------------- | --------- | ---------- |
| BYOL | [byol_resnet50_8xb32-accum16-coslr-200e_in1k](../configs/selfsup/byol/byol_resnet50_8xb32-accum16-coslr-200e_in1k.py) | | |
| DeepCLuster | [deepcluster-sobel_resnet50_8xb64-steplr-200e_in1k](../configs/selfsup/deepcluster/deepcluster-sobel_resnet50_8xb64-steplr-200e_in1k.py) | | |
| BYOL | [byol_resnet50_8xb32-accum16-coslr-200e_in1k](../configs/selfsup/byol/byol_resnet50_8xb32-accum16-coslr-200e_in1k.py) | 40.9 | 36.8 |
| DenseCL | [densecl_resnet50_8xb32-coslr-200e_in1k](../configs/selfsup/densecl/densecl_resnet50_8xb32-coslr-200e_in1k.py) | | |
| MoCo v2 | [mocov2_resnet50_8xb32-coslr-200e_in1k](../configs/selfsup/moco/mocov2_resnet50_8xb32-coslr-200e_in1k.py) | | |
| MoCo v2 | [mocov2_resnet50_8xb32-coslr-200e_in1k](../configs/selfsup/moco/mocov2_resnet50_8xb32-coslr-200e_in1k.py) | 40.2 | 36.1 |
| NPID | [npid_resnet50_8xb32-steplr-200e_in1k](../configs/selfsup/npid/npid_resnet50_8xb32-steplr-200e_in1k.py) | | |
| | [npid-ensure-neg_resnet50_8xb32-steplr-200e_in1k](../configs/selfsup/npid/npid-ensure-neg_resnet50_8xb32-steplr-200e_in1k.py) | | |
| ODC | [odc_resnet50_8xb64-steplr-440e_in1k](../configs/selfsup/odc/odc_resnet50_8xb64-steplr-440e_in1k.py) | | |
| Relative Location | [relative-loc_resnet50_8xb64-steplr-70e_in1k](../configs/selfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k.py) | | |
| Rotation Prediction | [rotation-pred_resnet50_8xb16-steplr-70e_in1k](../configs/selfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k.py) | | |
| SimCLR | [simclr_resnet50_8xb32-coslr-200e_in1k](../configs/selfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k.py) | | |
| SimSiam | [simsiam_resnet50_8xb32-coslr-100e_in1k](../configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py) | | |
| | [simsiam_resnet50_8xb32-coslr-200e_in1k](../configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py) | | |
| SwAV | [swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96](../configs/selfsup/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96.py) | | |
| Relative Location | [relative-loc_resnet50_8xb64-steplr-70e_in1k](../configs/selfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k.py) | 37.5 | 33.7 |
| Rotation Prediction | [rotation-pred_resnet50_8xb16-steplr-70e_in1k](../configs/selfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k.py) | 37.9 | 34.2 |
| SimCLR | [simclr_resnet50_8xb32-coslr-200e_in1k](../configs/selfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k.py) | 38.7 | 34.9 |
| SimSiam | [simsiam_resnet50_8xb32-coslr-100e_in1k](../configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py) | 38.3 | 34.4 |
| | [simsiam_resnet50_8xb32-coslr-200e_in1k](../configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py) | 38.8 | 34.9 |
| SwAV | [swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96](../configs/selfsup/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96.py) | 40.2 | 36.3 |
### Pascal VOC12 Aug Segmentation
@ -79,7 +74,6 @@ In Pascal VOC12 Aug Segmentation task, we choose the evluation protocol from [MM
| DenseCL | [densecl_resnet50_8xb32-coslr-200e_in1k](../configs/selfsup/densecl/densecl_resnet50_8xb32-coslr-200e_in1k.py) | 69.47 |
| MoCo v2 | [mocov2_resnet50_8xb32-coslr-200e_in1k](../configs/selfsup/moco/mocov2_resnet50_8xb32-coslr-200e_in1k.py) | 67.55 |
| NPID | [npid_resnet50_8xb32-steplr-200e_in1k](../configs/selfsup/npid/npid_resnet50_8xb32-steplr-200e_in1k.py) | 65.45 |
| | [npid-ensure-neg_resnet50_8xb32-steplr-200e_in1k](../configs/selfsup/npid/npid-ensure-neg_resnet50_8xb32-steplr-200e_in1k.py) | 64.73 |
| ODC | [odc_resnet50_8xb64-steplr-440e_in1k](../configs/selfsup/odc/odc_resnet50_8xb64-steplr-440e_in1k.py) | 54.76 |
| Relative Location | [relative-loc_resnet50_8xb64-steplr-70e_in1k](../configs/selfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k.py) | 63.49 |
| Rotation Prediction | [rotation-pred_resnet50_8xb16-steplr-70e_in1k](../configs/selfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k.py) | 64.31 |