SLiMe: Segment Like Me

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Khani, Aliasghar, Taghanaki, Saeid Asgari, Sanghi, Aditya, Amiri, Ali Mahdavi, Hamarneh, Ghassan
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911796834598912
author Khani, Aliasghar
Taghanaki, Saeid Asgari
Sanghi, Aditya
Amiri, Ali Mahdavi
Hamarneh, Ghassan
author_facet Khani, Aliasghar
Taghanaki, Saeid Asgari
Sanghi, Aditya
Amiri, Ali Mahdavi
Hamarneh, Ghassan
contents Significant strides have been made using large vision-language models, like Stable Diffusion (SD), for a variety of downstream tasks, including image editing, image correspondence, and 3D shape generation. Inspired by these advancements, we explore leveraging these extensive vision-language models for segmenting images at any desired granularity using as few as one annotated sample by proposing SLiMe. SLiMe frames this problem as an optimization task. Specifically, given a single training image and its segmentation mask, we first extract attention maps, including our novel "weighted accumulated self-attention map" from the SD prior. Then, using the extracted attention maps, the text embeddings of Stable Diffusion are optimized such that, each of them, learn about a single segmented region from the training image. These learned embeddings then highlight the segmented region in the attention maps, which in turn can then be used to derive the segmentation map. This enables SLiMe to segment any real-world image during inference with the granularity of the segmented region in the training image, using just one example. Moreover, leveraging additional training data when available, i.e. few-shot, improves the performance of SLiMe. We carried out a knowledge-rich set of experiments examining various design factors and showed that SLiMe outperforms other existing one-shot and few-shot segmentation methods.
format Preprint
id arxiv_https___arxiv_org_abs_2309_03179
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle SLiMe: Segment Like Me
Khani, Aliasghar
Taghanaki, Saeid Asgari
Sanghi, Aditya
Amiri, Ali Mahdavi
Hamarneh, Ghassan
Computer Vision and Pattern Recognition
Machine Learning
Significant strides have been made using large vision-language models, like Stable Diffusion (SD), for a variety of downstream tasks, including image editing, image correspondence, and 3D shape generation. Inspired by these advancements, we explore leveraging these extensive vision-language models for segmenting images at any desired granularity using as few as one annotated sample by proposing SLiMe. SLiMe frames this problem as an optimization task. Specifically, given a single training image and its segmentation mask, we first extract attention maps, including our novel "weighted accumulated self-attention map" from the SD prior. Then, using the extracted attention maps, the text embeddings of Stable Diffusion are optimized such that, each of them, learn about a single segmented region from the training image. These learned embeddings then highlight the segmented region in the attention maps, which in turn can then be used to derive the segmentation map. This enables SLiMe to segment any real-world image during inference with the granularity of the segmented region in the training image, using just one example. Moreover, leveraging additional training data when available, i.e. few-shot, improves the performance of SLiMe. We carried out a knowledge-rich set of experiments examining various design factors and showed that SLiMe outperforms other existing one-shot and few-shot segmentation methods.
title SLiMe: Segment Like Me
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2309.03179