CVAug 23, 2023

Diffusion-based Image Translation with Label Guidance for Domain Adaptive Semantic Segmentation

arXiv:2308.12350v142 citationsh-index: 64
Originality Highly original
AI Analysis

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes