Advanced Feature Manipulation for Enhanced Change Detection Leveraging Natural Language Models

TL;DR

This paper introduces a novel change detection method that leverages large language models to manipulate feature maps, improving semantic relevance in bi-temporal image analysis.

Contribution

It presents a new approach that focuses on feature map manipulation from pre-trained LLMs, unlike prior methods that only extract features.

Findings

Enhanced change detection accuracy demonstrated

Effective manipulation of feature maps improves semantic relevance

Outperforms existing LLM-based change detection methods

Abstract

Change detection is a fundamental task in computer vision that processes a bi-temporal image pair to differentiate between semantically altered and unaltered regions. Large language models (LLMs) have been utilized in various domains for their exceptional feature extraction capabilities and have shown promise in numerous downstream applications. In this study, we harness the power of a pre-trained LLM, extracting feature maps from extensive datasets, and employ an auxiliary network to detect changes. Unlike existing LLM-based change detection methods that solely focus on deriving high-quality feature maps, our approach emphasizes the manipulation of these feature maps to enhance semantic relevance.