Currently, self-supervised representation learning is mainly tested on image classification tasks, which is not insufficient to verify its effectiveness. It should also be tested in the visual matching task, and pedestrian re-recognition is just such an appropriate task.
MoCo v2 is an improved version of the Momentum Contrast self-supervised learning algorithm. Motivated by the findings presented in the SimCLR paper, authors: - Replace the 1-layer fully connected layer with a 2-layer MLP head with ReLU for the unsupervised training stage. - Include blur augmentation. - Use cosine learning rate schedule. These modifications enable MoCo to outperform the state-of-the-art SimCLR with a smaller batch size and fewer epochs.