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.
Sang ngôn ngữ khác
từ nội dung nguồn
arxiv.org
Thông tin chi tiết chính được chắt lọc từ
by Jiayi Ni,Sen... lúc arxiv.org 04-01-2024
https://arxiv.org/pdf/2309.13604.pdfYêu cầu sâu hơn