Self-Supervised Person Re-Identification
4 papers with code • 1 benchmarks • 1 datasets
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.
From an augmented view of an image, we train the online network to predict the target network representation of the same image under a different augmented view.
In this paper, we reveal two contradictory phenomena in contrastive learning that we call under-clustering and over-clustering problems, which are major obstacles to learning efficiency.