{"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/convolutional-lstms-for-cloud-robust","title":"Convolutional LSTMs for Cloud-Robust Segmentation of Remote Sensing Imagery","arxiv_id":"1811.02471","date":"2018-10-28","proceeding":null,"authors":["Marc Rußwurm","Marco Körner"],"abstract":"Clouds frequently cover the Earth's surface and pose an omnipresent challenge\nto optical Earth observation methods. The vast majority of remote sensing\napproaches either selectively choose single cloud-free observations or employ a\npre-classification strategy to identify and mask cloudy pixels. We follow a\ndifferent strategy and treat cloud coverage as noise that is inherent to the\nobserved satellite data. In prior work, we directly employed a straightforward\n\\emph{convolutional long short-term memory} network for vegetation\nclassification without explicit cloud filtering and achieved state-of-the-art\nclassification accuracies. In this work, we investigate this cloud-robustness\nfurther by visualizing internal cell activations and performing an ablation\nexperiment on datasets of different cloud coverage. In the visualizations of\nnetwork states, we identified some cells in which modulation and input gates\nclosed on cloudy pixels. This indicates that the network has internalized a\ncloud-filtering mechanism without being specifically trained on cloud labels.\nOverall, our results question the necessity of sophisticated pre-processing\npipelines for multi-temporal deep learning approaches.","url_abs":"http://arxiv.org/abs/1811.02471v2","url_pdf":"http://arxiv.org/pdf/1811.02471v2.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":"convolutional-lstms-for-cloud-robust","repo_url":"https://github.com/TUM-LMF/MTLCC","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"earth-observation","task_name":"Earth Observation"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"segmentation-of-remote-sensing-imagery","task_name":"Segmentation Of Remote Sensing Imagery"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.02471","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.02471"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/TUM-LMF/MTLCC","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"080549f525d580a0","entry":"norm_ptp","repo":"TUM-LMF/MTLCC","repo_kind":"official","path":"utils/interactive_plotting.py","file_url":"https://github.com/TUM-LMF/MTLCC/blob/HEAD/utils/interactive_plotting.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"080549f525d580a0"}},{"code_sha256_prefix":"3a4b51c9a8d7694d","entry":"norm_std","repo":"TUM-LMF/MTLCC","repo_kind":"official","path":"utils/interactive_plotting.py","file_url":"https://github.com/TUM-LMF/MTLCC/blob/HEAD/utils/interactive_plotting.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3a4b51c9a8d7694d"}},{"code_sha256_prefix":"526a39c11c2a188a","entry":"remove_padded_instances","repo":"TUM-LMF/MTLCC","repo_kind":"official","path":"tfrecord2tif.py","file_url":"https://github.com/TUM-LMF/MTLCC/blob/HEAD/tfrecord2tif.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"526a39c11c2a188a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}