The paper proposes a distribution-aware tuning (DAT) method for efficient and stable continual test-time adaptation (CTTA) in semantic segmentation tasks.
The key highlights are:
DAT adaptively selects two small groups of trainable parameters (around 5%) based on the degree of pixel-level distribution shifts in the target domain:
The Parameter Accumulation Update (PAU) strategy is introduced to efficiently collect the DSP and TRP during the continual adaptation process. For each target domain sample, only a very small fraction of parameters (e.g., 0.1%) are selected and added to the parameter group until the distribution shift becomes relatively small.
Extensive experiments on two CTTA benchmarks, Cityscape-ACDC and SHIFT, demonstrate that DAT achieves competitive performance and efficiency compared to previous state-of-the-art methods, showcasing its effectiveness in addressing the semantic segmentation CTTA problem.
In un'altra lingua
dal contenuto originale
arxiv.org
Approfondimenti chiave tratti da
by Jiayi Ni,Sen... alle arxiv.org 04-01-2024
https://arxiv.org/pdf/2309.13604.pdfDomande più approfondite