Saved in:
Bibliographic Details
Main Authors: Tang, Luyao, Yuan, Yuxuan, Chen, Chaoqi, Huang, Kunze, Ding, Xinghao, Huang, Yue
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.16310
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914928751804416
author Tang, Luyao
Yuan, Yuxuan
Chen, Chaoqi
Huang, Kunze
Ding, Xinghao
Huang, Yue
author_facet Tang, Luyao
Yuan, Yuxuan
Chen, Chaoqi
Huang, Kunze
Ding, Xinghao
Huang, Yue
contents Foundation models have made incredible strides in achieving zero-shot or few-shot generalization, leveraging prompt engineering to mimic the problem-solving approach of human intelligence. However, when it comes to some foundation models like Segment Anything, there is still a challenge in performing well on out-of-distribution data, including camouflaged and medical images. Inconsistent prompting strategies during fine-tuning and testing further compound the issue, leading to decreased performance. Drawing inspiration from how human cognition processes new environments, we introduce SlotSAM, a method that reconstructs features from the encoder in a self-supervised manner to create object-centric representations. These representations are then integrated into the foundation model, bolstering its object-level perceptual capabilities while reducing the impact of distribution-related variables. The beauty of SlotSAM lies in its simplicity and adaptability to various tasks, making it a versatile solution that significantly enhances the generalization abilities of foundation models. Through limited parameter fine-tuning in a bootstrap manner, our approach paves the way for improved generalization in novel environments. The code is available at github.com/lytang63/SlotSAM.
format Preprint
id arxiv_https___arxiv_org_abs_2408_16310
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Bootstrap Segmentation Foundation Model under Distribution Shift via Object-Centric Learning
Tang, Luyao
Yuan, Yuxuan
Chen, Chaoqi
Huang, Kunze
Ding, Xinghao
Huang, Yue
Computer Vision and Pattern Recognition
Foundation models have made incredible strides in achieving zero-shot or few-shot generalization, leveraging prompt engineering to mimic the problem-solving approach of human intelligence. However, when it comes to some foundation models like Segment Anything, there is still a challenge in performing well on out-of-distribution data, including camouflaged and medical images. Inconsistent prompting strategies during fine-tuning and testing further compound the issue, leading to decreased performance. Drawing inspiration from how human cognition processes new environments, we introduce SlotSAM, a method that reconstructs features from the encoder in a self-supervised manner to create object-centric representations. These representations are then integrated into the foundation model, bolstering its object-level perceptual capabilities while reducing the impact of distribution-related variables. The beauty of SlotSAM lies in its simplicity and adaptability to various tasks, making it a versatile solution that significantly enhances the generalization abilities of foundation models. Through limited parameter fine-tuning in a bootstrap manner, our approach paves the way for improved generalization in novel environments. The code is available at github.com/lytang63/SlotSAM.
title Bootstrap Segmentation Foundation Model under Distribution Shift via Object-Centric Learning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.16310