Vision-language models suffer significant accuracy drops under common corruptions. While test-time adaptation (TTA) successfully mitigates these shifts in CLIP-like contrastive models, its application to generative multimodal large language models (MLLMs) remains underexplored and uniquely challenging due to their sequ...
Mikolaj Piórczynski, Wojciech Masarczyk, Damian Sójka et al.· 0 citations
PACE is introduced, a backpropagation-free continual test-time adaptation system that directly optimizes the affine parameters of normalization layers that achieves state-of-the-art accuracy across multiple benchmarks under continual distribution shifts, reducing runtime by over 50% compared to existing backpropagation...
Damian Sójka, Sebastian Cygert, Marc Masana· arXiv.org· 1 citation
This work challenges the common strategy of setting the teacher weights to an exponential moving average of the student by showing that error accumulation still occurs, although it is mostly apparent on longer sequences compared to those commonly utilized, and proposes an intransigent teacher that does not update its w...
Damian Sójka, Marc Masana, Bartłomiej Twardowski et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.