Saved in:
Bibliographic Details
Main Authors: Dai, Jiayue, Wang, Yunya, Fang, Yihan, Chen, Yuetong, Xiong, Butian
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.15060
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910907885420544
author Dai, Jiayue
Wang, Yunya
Fang, Yihan
Chen, Yuetong
Xiong, Butian
author_facet Dai, Jiayue
Wang, Yunya
Fang, Yihan
Chen, Yuetong
Xiong, Butian
contents To address the semantic inconsistency issue with SAM or other single-image segmentation models handling image sequences, we introduce BYOCL. This novel model outperforms SAM in extensive experiments, showcasing its Hierarchical prototype capabilities across CLIP and other representations. BYOCL significantly reduces time and space consumption by dividing inputs into smaller batches, achieving exponential time reduction compared to previous methods. Our approach leverages the SAM image encoder for feature extraction, followed by Intra-Batch and Inter-Batch clustering algorithms. Extensive experiments demonstrate that BYOCL far exceeds the previous state-of-the-art single image segmentation model. Our work is the first to apply consistent segmentation using foundation models without requiring training, utilizing plug-and-play modules for any latent space, making our method highly efficientModels are available at \href{https://github.com/cyt1202/BYOCL.git
format Preprint
id arxiv_https___arxiv_org_abs_2410_15060
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle BYOCL: Build Your Own Consistent Latent with Hierarchical Representative Latent Clustering
Dai, Jiayue
Wang, Yunya
Fang, Yihan
Chen, Yuetong
Xiong, Butian
Computer Vision and Pattern Recognition
To address the semantic inconsistency issue with SAM or other single-image segmentation models handling image sequences, we introduce BYOCL. This novel model outperforms SAM in extensive experiments, showcasing its Hierarchical prototype capabilities across CLIP and other representations. BYOCL significantly reduces time and space consumption by dividing inputs into smaller batches, achieving exponential time reduction compared to previous methods. Our approach leverages the SAM image encoder for feature extraction, followed by Intra-Batch and Inter-Batch clustering algorithms. Extensive experiments demonstrate that BYOCL far exceeds the previous state-of-the-art single image segmentation model. Our work is the first to apply consistent segmentation using foundation models without requiring training, utilizing plug-and-play modules for any latent space, making our method highly efficientModels are available at \href{https://github.com/cyt1202/BYOCL.git
title BYOCL: Build Your Own Consistent Latent with Hierarchical Representative Latent Clustering
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.15060