MoCo-v2 ResNet-50 (200 epochs, 256 bs) achieves 83.2% Top 1 Accuracy on ImageNet
| Training Techniques | MoCo v2, Weight Decay, SGD with Momentum |
|---|---|
| Architecture | 1x1 Convolution, Bottleneck Residual Block, Batch Normalization, Convolution, Global Average Pooling, Residual Block, Residual Connection, ReLU, Max Pooling, Softmax |
| ID | rn50_moco_in1k_moco_style |
| SHOW MORE |
MoCo v2 is an improved version of the Momentum Contrast self-supervised learning algorithm. Improvements include:
Get started with VISSL by trying one of the Colab tutorial notebooks.
@misc{chen2020improved,
title={Improved Baselines with Momentum Contrastive Learning},
author={Xinlei Chen and Haoqi Fan and Ross Girshick and Kaiming He},
year={2020},
eprint={2003.04297},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
Image Classification
| BENCHMARK | MODEL | METRIC NAME | METRIC VALUE | GLOBAL RANK |
|---|---|---|---|---|
| ImageNet | MoCo-v2 ResNet-50 (200 epochs, 256 bs) | Top 1 Accuracy | 66.4% | # 291 |
