Self-supervisedCo-training forVideoRepresentationLearning

Weshowthattheanswerisno,intworespects: First, we show that hard positives are being neglected in the self-supervised training, and that if these hard positives are included then the quality of learnt representation improves significantly. Toinvestigatethis,weconduct anoracleexperiment where positivesamples areincorporated into the instance-based training process based on the semantic class label.