Emerging Properties in Self-Supervised Vision Transformers — mentioned by albertzeyer

Tue, 18 Nov 2025 08:53:01 GMT

This idea is often used for self-supervised learning (SSL). E.g. see DINO (https://arxiv.org/abs/2104.14294).

Paper and discussion history. A mention is not an endorsement.

Emerging Properties in Self-Supervised Vision Transformers — mentioned by albertzeyer

Tue, 18 Nov 2025 08:49:24 GMT

The random noise is added to the model parameters, not the inputs, or not? This reminds me of variational noise (https://www.cs.toronto.edu/~graves/nips_2011.pdf). If it is random noise on the input, it would be like many of the SSL methods, e.g. DINO (https://arxiv.org/abs/2104.14294), right?

Paper and discussion history. A mention is not an endorsement.

Emerging Properties in Self-Supervised Vision Transformers · HackerPapers discussions

Emerging Properties in Self-Supervised Vision Transformers — mentioned by albertzeyer

Emerging Properties in Self-Supervised Vision Transformers — mentioned by albertzeyer