MoCo v2 is an improved version of the Momentum Contrast self-supervised learning algorithm. Motivated by the findings presented in the SimCLR paper, authors:
These modifications enable MoCo to outperform the state-of-the-art SimCLR with a smaller batch size and fewer epochs.
Source: Improved Baselines with Momentum Contrastive LearningPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Self-Supervised Learning | 13 | 21.31% |
Image Classification | 7 | 11.48% |
Object Detection | 5 | 8.20% |
Semantic Segmentation | 5 | 8.20% |
Classification | 3 | 4.92% |
Instance Segmentation | 2 | 3.28% |
Self-Supervised Image Classification | 2 | 3.28% |
Unsupervised Pre-training | 2 | 3.28% |
Semi-Supervised Image Classification | 2 | 3.28% |
Component | Type |
|
---|---|---|
![]() |
Feedforward Networks | |
![]() |
Loss Functions | |
![]() |
Image Data Augmentation |