# C-SAW: Self-Supervised Prompt Learning for Image Generalization in Remote Sensing

arXiv: https://arxiv.org/abs/2311.15812 · HTML: https://mlsanity.com/paper/2311.15812/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 59 of its 91 references that are in the map.
- First posted on arXiv 27 Nov 2023.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 30 of 59)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [Contrastive Multiview Coding](https://mlsanity.com/paper/1906.05849/) (2019)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [Open-vocabulary Object Detection via Vision and Language Knowledge Distillation](https://mlsanity.com/paper/2104.13921/) (2021)
- [Show and Tell: A Neural Image Caption Generator](https://mlsanity.com/paper/1411.4555/) (2014)
- [Remote Sensing Image Scene Classification: Benchmark and State of the Art](https://mlsanity.com/paper/1703.00121/) (2017)
- [Learning to Generalize: Meta-Learning for Domain Generalization](https://mlsanity.com/paper/1710.03463/) (2017)
- [Domain Generalization with MixStyle](https://mlsanity.com/paper/2104.02008/) (2021)
- [SLIP: Self-supervision meets Language-Image Pre-training](https://mlsanity.com/paper/2112.12750/) (2021)
- [Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling](https://mlsanity.com/paper/2111.03930/) (2021)
- [Self-Challenging Improves Cross-Domain Generalization](https://mlsanity.com/paper/2007.02454/) (2020)
- [SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery](https://mlsanity.com/paper/2207.08051/) (2022)
- [Domain Generalization via Model-Agnostic Learning of Semantic Features](https://mlsanity.com/paper/1910.13580/) (2019)
- [Wasserstein Auto-Encoders](https://mlsanity.com/paper/1711.01558/) (2017)

## Built on by (most cited first, 6 of 6)

- [Mind the Modality Gap: Towards a Remote Sensing Vision-Language Model via Cross-modal Alignment](https://mlsanity.com/paper/2402.09816/) (2024)
- [GRASP: Guided Region-Aware Sparse Prompting for Adapting MLLMs to Remote Sensing](https://mlsanity.com/paper/2601.17089/) (2026)
- [FrogDogNet: Fourier frequency Retained visual prompt Output Guidance for Domain Generalization of CLIP in Remote Sensing](https://mlsanity.com/paper/2504.16433/) (2025)
- [GraphVL: Graph-Enhanced Semantic Modeling via Vision-Language Models for Generalized Class Discovery](https://mlsanity.com/paper/2411.02074/) (2024)
- [bi-modal textual prompt learning for vision-language models in remote sensing](https://mlsanity.com/paper/2601.20675/) (2026)
- [A Benchmark of Generative Methods for Zero-Shot Environmental Sound Classification](https://mlsanity.com/paper/2412.03771/) (2024)

## Abstract (arXiv)

We focus on domain and class generalization problems in analyzing optical remote sensing images, using the large-scale pre-trained vision-language model (VLM), CLIP. While contrastively trained VLMs show impressive zero-shot generalization performance, their effectiveness is limited when dealing with diverse domains during training and testing. Existing prompt learning techniques overlook the importance of incorporating domain and content information into the prompts, which results in a drop in performance while dealing with such multi-domain data. To address these challenges, we propose a solution that ensures domain-invariant prompt learning while enhancing the expressiveness of visual features. We observe that CLIP's vision encoder struggles to identify contextual image information, particularly when image patches are jumbled up. This issue is especially severe in optical remote sensing images, where land-cover classes exhibit well-defined contextual appearances. To this end, we introduce C-SAW, a method that complements CLIP with a self-supervised loss in the visual space and a novel prompt learning technique that emphasizes both visual domain and content-specific features. We keep the CLIP backbone frozen and introduce a small set of projectors for both the CLIP encoders to train C-SAW contrastively. Experimental results demonstrate the superiority of C-SAW across multiple remote sensing benchmarks and different generalization tasks.