Publication

SLiMe

Segment Like Me

Using just one user-annotated image with various granularities (as shown in the leftmost column), SLiMe can segment different test images in accordance with those same granularities (as depicted in the other columns).

Abstract

SLiMe: Segment Like Me

Aliasghar Khani, Saeid Asgari , Aditya Sanghi, Ali Mahdavi-Amiri, Ghassan Hamarneh

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.

Download publication

Associated Researchers

Aliasghar Khani

School of Computing Science, Simon Fraser University

Ali Mahdavi-Amiri

School of Computing Science, Simon Fraser University

Ghassan Hamarneh

School of Computing Science, Simon Fraser University

View all researchers

Related Resources

Project

2022

Systems Design and Simulation

Predictive models of complex systems will require a more scalable,…

Project

2014

Multi-touch

An investigation of new user interface designs and interaction…

Project

2016

HIVE Exhibit

Hive is an innovative and interactive exhibit built through a unique…

Project

2022

Building Simulation

With simulation results in hand, an architect can better predict the…

Get in touch

Something pique your interest? Get in touch if you’d like to learn more about Autodesk Research, our projects, people, and potential collaboration opportunities.

Contact us