Diffusion-based Image Translation with Label Guidance for Domain Adaptive Semantic Segmentation
This addresses domain adaptation for semantic segmentation, which is incremental as it builds on existing translation strategies.
The paper tackled the problem of preserving semantically-consistent local details in domain adaptive semantic segmentation by using source-domain labels as guidance during image translation, resulting in superior performance over state-of-the-art methods in extensive experiments.
Translating images from a source domain to a target domain for learning target models is one of the most common strategies in domain adaptive semantic segmentation (DASS). However, existing methods still struggle to preserve semantically-consistent local details between the original and translated images. In this work, we present an innovative approach that addresses this challenge by using source-domain labels as explicit guidance during image translation. Concretely, we formulate cross-domain image translation as a denoising diffusion process and utilize a novel Semantic Gradient Guidance (SGG) method to constrain the translation process, conditioning it on the pixel-wise source labels. Additionally, a Progressive Translation Learning (PTL) strategy is devised to enable the SGG method to work reliably across domains with large gaps. Extensive experiments demonstrate the superiority of our approach over state-of-the-art methods.