Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training?

Self-supervision is a powerful technique for learning visual representations from unlabeled data. Existing techniques primarily adopt a two-stage approach for self-supervised learning (SSL): a pretraining stage on unlabeled data followed by a finetuning stage on labeled data.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

• computer-vision
• fine-tuning
• benchmarks