ZoRI: Towards Discriminative Zero-Shot Remote Sensing Instance Segmentation

TL;DR

This paper introduces ZoRI, a novel framework for zero-shot remote sensing instance segmentation that enhances class discrimination and domain adaptation, enabling the identification of unseen aerial objects with state-of-the-art performance.

Contribution

The paper proposes a discrimination-enhanced classifier and a knowledge-maintained adaptation strategy tailored for zero-shot remote sensing segmentation, addressing domain gap and class similarity challenges.

Findings

ZoRI achieves state-of-the-art results on zero-shot remote sensing segmentation benchmarks.

The framework effectively leverages refined textual embeddings and aerial prototypes.

Experimental results demonstrate significant improvements over existing methods.

Abstract

Instance segmentation algorithms in remote sensing are typically based on conventional methods, limiting their application to seen scenarios and closed-set predictions. In this work, we propose a novel task called zero-shot remote sensing instance segmentation, aimed at identifying aerial objects that are absent from training data. Challenges arise when classifying aerial categories with high inter-class similarity and intra-class variance. Besides, the domain gap between vision-language models' pretraining datasets and remote sensing datasets hinders the zero-shot capabilities of the pretrained model when it is directly applied to remote sensing images. To address these challenges, we propose a $\textbf{Z}$ero-Sh$\textbf{o}$t $\textbf{R}$emote Sensing $\textbf{I}$nstance Segmentation framework, dubbed $\textbf{ZoRI}$. Our approach features a discrimination-enhanced classifier that uses refined textual embeddings to increase the awareness of class disparities. Instead of direct fine-tuning, we propose a knowledge-maintained adaptation strategy that decouples semantic-related information to preserve the pretrained vision-language alignment while adjusting features to capture remote sensing domain-specific visual cues. Additionally, we introduce a prior-injected prediction with cache bank of aerial visual prototypes to supplement the semantic richness of text embeddings and seamlessly integrate aerial representations, adapting to the remote sensing domain. We establish new experimental protocols and benchmarks, and extensive experiments convincingly demonstrate that ZoRI achieves the state-of-art performance on the zero-shot remote sensing instance segmentation task. Our code is available at https://github.com/HuangShiqi128/ZoRI.