International Conference on Learning Representations (ICLR) 2024
SLiMe
Segment Like Me
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 publicationAssociated Researchers
Ali Mahdavi-Amiri
School of Computing Science, Simon Fraser University
Ghassan Hamarneh
School of Computing Science, Simon Fraser University
Related Resources
2024
Exploring Opportunities for Adopting Generative AI in Automotive Conceptual DesignThis research discusses opportunities for adopting generative AI in…
2022
CAPRI-Net: Learning Compact CAD Shapes with Adaptive Primitive AssemblyWe introduce CAPRI-Net, a self-supervised neural net-work for learning…
2022
Systems Design and SimulationPredictive models of complex systems will require a more scalable,…
2017
Project Dreamcatcher: Generative Design Solutions in CADWhat if a CAD system could generate thousands of design options that…
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