FCC: Fully Connected Correlation for One-Shot Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Moon, Seonghyeon, Kong, Haein, Khan, Muhammad Haris, Kapadia, Mubbasir, Lin, Yuewei
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912803162423296
author Moon, Seonghyeon
Kong, Haein
Khan, Muhammad Haris
Kapadia, Mubbasir
Lin, Yuewei
author_facet Moon, Seonghyeon
Kong, Haein
Khan, Muhammad Haris
Kapadia, Mubbasir
Lin, Yuewei
contents Few-shot segmentation (FSS) aims to segment the target object in a query image using only a small set of support images and masks. Therefore, having strong prior information for the target object using the support set is essential for guiding the initial training of FSS, which leads to the success of few-shot segmentation in challenging cases, such as when the target object shows considerable variation in appearance, texture, or scale across the support and query images. Previous methods have tried to obtain prior information by creating correlation maps from pixel-level correlation on final-layer or same-layer features. However, we found these approaches can offer limited and partial information when advanced models like Vision Transformers are used as the backbone. Vision Transformer encoders have a multi-layer structure with identical shapes in their intermediate layers. Leveraging the feature comparison from all layers in the encoder can enhance the performance of few-shot segmentation. We introduce FCC (Fully Connected Correlation) to integrate pixel-level correlations between support and query features, capturing associations that reveal target-specific patterns and correspondences in both same-layers and cross-layers. FCC captures previously inaccessible target information, effectively addressing the limitations of support mask. Our approach consistently demonstrates state-of-the-art performance on PASCAL, COCO, and domain shift tests. We conducted an ablation study and cross-layer correlation analysis to validate FCC's core methodology. These findings reveal the effectiveness of FCC in enhancing prior information and overall model performance.
format Preprint
id arxiv_https___arxiv_org_abs_2411_11917
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FCC: Fully Connected Correlation for One-Shot Segmentation
Moon, Seonghyeon
Kong, Haein
Khan, Muhammad Haris
Kapadia, Mubbasir
Lin, Yuewei
Computer Vision and Pattern Recognition
Few-shot segmentation (FSS) aims to segment the target object in a query image using only a small set of support images and masks. Therefore, having strong prior information for the target object using the support set is essential for guiding the initial training of FSS, which leads to the success of few-shot segmentation in challenging cases, such as when the target object shows considerable variation in appearance, texture, or scale across the support and query images. Previous methods have tried to obtain prior information by creating correlation maps from pixel-level correlation on final-layer or same-layer features. However, we found these approaches can offer limited and partial information when advanced models like Vision Transformers are used as the backbone. Vision Transformer encoders have a multi-layer structure with identical shapes in their intermediate layers. Leveraging the feature comparison from all layers in the encoder can enhance the performance of few-shot segmentation. We introduce FCC (Fully Connected Correlation) to integrate pixel-level correlations between support and query features, capturing associations that reveal target-specific patterns and correspondences in both same-layers and cross-layers. FCC captures previously inaccessible target information, effectively addressing the limitations of support mask. Our approach consistently demonstrates state-of-the-art performance on PASCAL, COCO, and domain shift tests. We conducted an ablation study and cross-layer correlation analysis to validate FCC's core methodology. These findings reveal the effectiveness of FCC in enhancing prior information and overall model performance.
title FCC: Fully Connected Correlation for One-Shot Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.11917