Open-Vocabulary Attention Maps with Token Optimization for Semantic Segmentation in Diffusion Models
This work addresses the problem of open-vocabulary segmentation in diffusion models for researchers and practitioners, offering an incremental improvement over existing methods.
The paper tackles the limitation of generating semantic segmentation masks only for prompt words in diffusion models by introducing Open-Vocabulary Attention Maps (OVAM) and a token optimization method, resulting in an mIoU improvement from 52.1 to 86.6 for pseudo-masks in synthetic images.
Diffusion models represent a new paradigm in text-to-image generation. Beyond generating high-quality images from text prompts, models such as Stable Diffusion have been successfully extended to the joint generation of semantic segmentation pseudo-masks. However, current extensions primarily rely on extracting attentions linked to prompt words used for image synthesis. This approach limits the generation of segmentation masks derived from word tokens not contained in the text prompt. In this work, we introduce Open-Vocabulary Attention Maps (OVAM)-a training-free method for text-to-image diffusion models that enables the generation of attention maps for any word. In addition, we propose a lightweight optimization process based on OVAM for finding tokens that generate accurate attention maps for an object class with a single annotation. We evaluate these tokens within existing state-of-the-art Stable Diffusion extensions. The best-performing model improves its mIoU from 52.1 to 86.6 for the synthetic images' pseudo-masks, demonstrating that our optimized tokens are an efficient way to improve the performance of existing methods without architectural changes or retraining.