{"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/transfer-learning-from-deep-features-for","title":"Transfer Learning from Deep Features for Remote Sensing and Poverty Mapping","arxiv_id":"1510.00098","date":"2015-10-01","proceeding":null,"authors":["Michael Xie","Neal Jean","Marshall Burke","David Lobell","Stefano Ermon"],"abstract":"The lack of reliable data in developing countries is a major obstacle to\nsustainable development, food security, and disaster relief. Poverty data, for\nexample, is typically scarce, sparse in coverage, and labor-intensive to\nobtain. Remote sensing data such as high-resolution satellite imagery, on the\nother hand, is becoming increasingly available and inexpensive. Unfortunately,\nsuch data is highly unstructured and currently no techniques exist to\nautomatically extract useful insights to inform policy decisions and help\ndirect humanitarian efforts. We propose a novel machine learning approach to\nextract large-scale socioeconomic indicators from high-resolution satellite\nimagery. The main challenge is that training data is very scarce, making it\ndifficult to apply modern techniques such as Convolutional Neural Networks\n(CNN). We therefore propose a transfer learning approach where nighttime light\nintensities are used as a data-rich proxy. We train a fully convolutional CNN\nmodel to predict nighttime lights from daytime imagery, simultaneously learning\nfeatures that are useful for poverty prediction. The model learns filters\nidentifying different terrains and man-made structures, including roads,\nbuildings, and farmlands, without any supervision beyond nighttime lights. We\ndemonstrate that these learned features are highly informative for poverty\nmapping, even approaching the predictive performance of survey data collected\nin the field.","url_abs":"http://arxiv.org/abs/1510.00098v2","url_pdf":"http://arxiv.org/pdf/1510.00098v2.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":"transfer-learning-from-deep-features-for","repo_url":"https://github.com/kushthedude/Poverty-Predictor","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"humanitarian","task_name":"Humanitarian"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1510.00098","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1510.00098"}},"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/kushthedude/Poverty-Predictor","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":2},"by_repo_kind":{"listed":{"samples":2,"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":"d5c9e48fb59c5fbc","entry":"compute_plot_params","repo":"kushthedude/Poverty-Predictor","repo_kind":"listed","path":"figures/fig_utils.py","file_url":"https://github.com/kushthedude/Poverty-Predictor/blob/HEAD/figures/fig_utils.py","link_basis":"harvester_set","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":"d5c9e48fb59c5fbc"}},{"code_sha256_prefix":"ffc36f8b2d7eabf8","entry":"load_and_reduce_country_by_percentile","repo":"kushthedude/Poverty-Predictor","repo_kind":"listed","path":"figures/fig_utils.py","file_url":"https://github.com/kushthedude/Poverty-Predictor/blob/HEAD/figures/fig_utils.py","link_basis":"harvester_set","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":"ffc36f8b2d7eabf8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}