# MT3: Meta Test-Time Training for Self-Supervised Test-Time Adaption Source: [MT3: Meta Test-Time Training for Self-Supervised Test-Time Adaption]() Collection index: [llms.txt]() Data updated: 2025-10-25T23:54:05.632Z Authors: Alexander Bartler, Andre B\\"uhler, Felix Wiewel, Mario D\\"obler, Bin Yang Published: 2021-03-30T09:33:38.000Z ## Abstract 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 the different task-specific models leads to higher performance on those tasks. During test-time a single unlabeled image is sufficient to adapt the meta-model parameters. This is achieved by minimizing only the self-supervised loss component resulting in a better prediction for that image. Our approach significantly improves the state-of-the-art results on the CIFAR-10-Corrupted image classification benchmark. Our implementation is available on GitHub. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()