MT3: Meta Test-Time Training for Self-Supervised Test-Time Adaption. (arXiv:2103.16201v2 [cs.CV] UPDATED)

An unresolved problem in Deep Learning is the ability of neural networks to
cope with domain shifts during test-time, imposed by commonly fixing network
parameters after training. Our proposed method Meta Test-Time Training (MT3),
however, breaks this paradigm and enables adaption at test-time. We combine
meta-learning, self-supervision and test-time training to learn to adapt to
unseen test distributions. By minimizing the self-supervised loss, we learn
task-specific model parameters for different tasks. A meta-model is optimized
such that its adaption to …

arxiv cv meta test time training