跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.20787 · v1

PhaseCLIP: Phase-Aware Frequency-Domain Adaptation of Vision-Language Models for Few-Shot Remote-Sensing Classification

首次提交 2026-11-16 17:34
版本更新 2026-11-16 17:34
雷达观测 2026-11-17 17:11
arXiv ↗PDF ↗

摘要

Remote-sensing (RS) image scene classification aims to assign a semantic category to an overhead image, and in practice must often do so from only a handful of labelled examples, since annotation requires expert interpretation and the resulting labels transfer poorly across sensors and regions. Recent progress has come from adapting vision-language models (VLMs) such as CLIP, through learned prompts or feature adapters. Although effective, these methods construct their representation entirely in the spatial domain. RS scenes are dominated by periodic texture and regular geometry, which the Fourier spectrum describes compactly through an amplitude component, carrying texture and contrast statistics, and a phase component, carrying spatial structure. Existing frequency-domain adaptation of VLMs either exploits amplitude alone or does not separate amplitude from phase, leaving the structural component unused. In this article, we propose PhaseCLIP, which inserts phase-capable spectral modules and a feature-gating module into a frozen CLIP visual encoder and trains only 1.30% of its parameters. Because the amplitude and phase pathways share an identical parameter layout, a single weight set is learned on phase and transferred exactly to amplitude, giving a two-stage scheme that adds no parameters. Experiments on five public RS datasets, EuroSAT, PatternNet, UC Merced, LSRS and RSSCN7, against eight baselines under a matched protocol, show that PhaseCLIP attains 84.28% mean accuracy and is the best method in 23 of 30 dataset-by-shot cells, with phase contributing 1.93 points overall and 4.36 points on the most difficult dataset. Because the modules act on the spectrum of image patches and transformer tokens and leave the text encoder untouched, the approach can be extended to other RS sensors and tasks, and to other domains in which class evidence lies in spatial structure.

作者备注:23 pages, 7 figures, 5 tables. Code will be released at https://github.com/miralab-ai/PhaseCLIP upon publication

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-16 17:34 · 最新观测版本

PhaseCLIP: Phase-Aware Frequency-Domain Adaptation of Vision-Language Models for Few-Shot Remote-Sensing Classification

Remote-sensing (RS) image scene classification aims to assign a semantic category to an overhead image, and in practice must often do so from only a handful of labelled examples, since annotation requires expert interpretation and the resulting labels transfer poorly across sensors and regions. Recent progress has come from adapting vision-language models (VLMs) such as CLIP, through learned prompts or feature adapters. Although effective, these methods construct their representation entirely in the spatial domain. RS scenes are dominated by periodic texture and regular geometry, which the Fourier spectrum describes compactly through an amplitude component, carrying texture and contrast statistics, and a phase component, carrying spatial structure. Existing frequency-domain adaptation of VLMs either exploits amplitude alone or does not separate amplitude from phase, leaving the structural component unused. In this article, we propose PhaseCLIP, which inserts phase-capable spectral modules and a feature-gating module into a frozen CLIP visual encoder and trains only 1.30% of its parameters. Because the amplitude and phase pathways share an identical parameter layout, a single weight set is learned on phase and transferred exactly to amplitude, giving a two-stage scheme that adds no parameters. Experiments on five public RS datasets, EuroSAT, PatternNet, UC Merced, LSRS and RSSCN7, against eight baselines under a matched protocol, show that PhaseCLIP attains 84.28% mean accuracy and is the best method in 23 of 30 dataset-by-shot cells, with phase contributing 1.93 points overall and 4.36 points on the most difficult dataset. Because the modules act on the spectrum of image patches and transformer tokens and leave the text encoder untouched, the approach can be extended to other RS sensors and tasks, and to other domains in which class evidence lies in spatial structure.

查看此版本解读 →查看此版本原文 ↗