{"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/cdchat-a-large-multimodal-model-for-remote","title":"CDChat: A Large Multimodal Model for Remote Sensing Change Description","arxiv_id":"2409.16261","date":"2024-09-24","proceeding":null,"authors":["Mubashir Noman","Noor Ahsan","Muzammal Naseer","Hisham Cholakkal","Rao Muhammad Anwer","Salman Khan","Fahad Shahbaz Khan"],"abstract":"Large multimodal models (LMMs) have shown encouraging performance in the natural image domain using visual instruction tuning. However, these LMMs struggle to describe the content of remote sensing images for tasks such as image or region grounding, classification, etc. Recently, GeoChat make an effort to describe the contents of the RS images. Although, GeoChat achieves promising performance for various RS tasks, it struggles to describe the changes between bi-temporal RS images which is a key RS task. This necessitates the development of an LMM that can describe the changes between the bi-temporal RS images. However, there is insufficiency of datasets that can be utilized to tune LMMs. In order to achieve this, we introduce a change description instruction dataset that can be utilized to finetune an LMM and provide better change descriptions for RS images. Furthermore, we show that the LLaVA-1.5 model, with slight modifications, can be finetuned on the change description instruction dataset and achieve favorably better performance.","url_abs":"https://arxiv.org/abs/2409.16261v1","url_pdf":"https://arxiv.org/pdf/2409.16261v1.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":"cdchat-a-large-multimodal-model-for-remote","repo_url":"https://github.com/techmn/cdchat","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2409.16261","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.16261"}},"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/techmn/cdchat","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":3,"ran":2,"unverified":2},"by_repo_kind":{"official":{"samples":7,"ran":5,"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":7,"samples":[{"code_sha256_prefix":"592b3c1a88f93d7c","entry":"expand2square","repo":"techmn/cdchat","repo_kind":"official","path":"cdchat/mm_utils.py","file_url":"https://github.com/techmn/cdchat/blob/HEAD/cdchat/mm_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"592b3c1a88f93d7c"}},{"code_sha256_prefix":"42a46570620cd9fa","entry":"get_chunk","repo":"techmn/cdchat","repo_kind":"official","path":"cdchat/eval/batch_cdchat_vqa.py","file_url":"https://github.com/techmn/cdchat/blob/HEAD/cdchat/eval/batch_cdchat_vqa.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"42a46570620cd9fa"}},{"code_sha256_prefix":"c3ee9d07c900dd55","entry":"load_image_from_base64","repo":"techmn/cdchat","repo_kind":"official","path":"cdchat/mm_utils.py","file_url":"https://github.com/techmn/cdchat/blob/HEAD/cdchat/mm_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c3ee9d07c900dd55"}},{"code_sha256_prefix":"ab382f4b6886dee2","entry":"process_images","repo":"techmn/cdchat","repo_kind":"official","path":"cdchat/mm_utils.py","file_url":"https://github.com/techmn/cdchat/blob/HEAD/cdchat/mm_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ab382f4b6886dee2"}},{"code_sha256_prefix":"076c252c52cbb161","entry":"split_list","repo":"techmn/cdchat","repo_kind":"official","path":"cdchat/eval/batch_cdchat_vqa.py","file_url":"https://github.com/techmn/cdchat/blob/HEAD/cdchat/eval/batch_cdchat_vqa.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"076c252c52cbb161"}},{"code_sha256_prefix":"37899f22fb191b37","entry":"pretty_print_semaphore","repo":"techmn/cdchat","repo_kind":"official","path":"cdchat/utils.py","file_url":"https://github.com/techmn/cdchat/blob/HEAD/cdchat/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"37899f22fb191b37"}},{"code_sha256_prefix":"f9939a84b9a65279","entry":"violates_moderation","repo":"techmn/cdchat","repo_kind":"official","path":"cdchat/utils.py","file_url":"https://github.com/techmn/cdchat/blob/HEAD/cdchat/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f9939a84b9a65279"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}