Attention as Annotation: Generating Images and Pseudo-masks for Weakly Supervised Semantic Segmentation with Diffusion

Although recent advancements in diffusion models enabled high-fidelity and diverse image generation, training of discriminative models largely depends on collections of massive real images and their manual annotation. Here, we present a training method for semantic segmentation that neither relies on real images nor manual annotation. The proposed method {\it attn2mask} utilizes images generated by a text-to-image diffusion model in combination with its internal text-to-image cross-attention as supervisory pseudo-masks. Since the text-to-image generator is trained with image-caption pairs but without pixel-wise labels, attn2mask can be regarded as a weakly supervised segmentation method overall. Experiments show that attn2mask achieves promising results in PASCAL VOC for not using real training data for segmentation at all, and it is also useful to scale up segmentation to a more-class scenario, i.e., ImageNet segmentation. It also shows adaptation ability with LoRA-based fine-tuning, which enables the transfer to a distant domain i.e., Cityscapes.