{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/self-supervised-vision-transformers-for-joint","title":"Self-supervised Vision Transformers for Joint SAR-optical Representation Learning","arxiv_id":"2204.05381","date":"2022-04-11","proceeding":null,"authors":["Yi Wang","Conrad M Albrecht","Xiao Xiang Zhu"],"abstract":"Self-supervised learning (SSL) has attracted much interest in remote sensing and earth observation due to its ability to learn task-agnostic representations without human annotation. While most of the existing SSL works in remote sensing utilize ConvNet backbones and focus on a single modality, we explore the potential of vision transformers (ViTs) for joint SAR-optical representation learning. Based on DINO, a state-of-the-art SSL algorithm that distills knowledge from two augmented views of an input image, we combine SAR and optical imagery by concatenating all channels to a unified input. Subsequently, we randomly mask out channels of one modality as a data augmentation strategy. While training, the model gets fed optical-only, SAR-only, and SAR-optical image pairs learning both inner- and intra-modality representations. Experimental results employing the BigEarthNet-MM dataset demonstrate the benefits of both, the ViT backbones and the proposed multimodal SSL algorithm DINO-MM.","url_abs":"https://arxiv.org/abs/2204.05381v4","url_pdf":"https://arxiv.org/pdf/2204.05381v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"self-supervised-vision-transformers-for-joint","repo_url":"https://github.com/zhu-xlab/dino-mm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"self-supervised-vision-transformers-for-joint","repo_url":"https://github.com/zhu-xlab/ssl4eo-review","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"earth-observation","task_name":"Earth Observation"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sensor-dropout","method_name":"Sensor Dropout"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[{"slug":"sensor-dropout","name":"Sensor Dropout","full_name":"Sensor Dropout or SensD"}],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2204.05381","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}