{"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/lvlm-count-enhancing-the-counting-ability-of","title":"LVLM-COUNT: Enhancing the Counting Ability of Large Vision-Language Models","arxiv_id":"2412.00686","date":"2024-12-01","proceeding":null,"authors":["Muhammad Fetrat Qharabagh","Mohammadreza Ghofrani","Kimon Fountoulakis"],"abstract":"Counting is a fundamental operation for various visual tasks in real-life applications, requiring both object recognition and robust counting capabilities. Despite their advanced visual perception, large vision-language models (LVLMs) struggle with counting tasks, especially when the number of objects exceeds those commonly encountered during training. We enhance LVLMs' counting abilities using a divide-and-conquer approach, breaking counting problems into sub-counting tasks. Our method employs a mechanism that prevents bisecting and thus repetitive counting of objects, which occurs in a naive divide-and-conquer approach. Unlike prior methods, which do not generalize well to counting datasets they have not been trained on, our method performs well on new datasets without any additional training or fine-tuning. We demonstrate that our approach enhances the counting capability of LVLMs across various datasets and benchmarks.","url_abs":"https://arxiv.org/abs/2412.00686v2","url_pdf":"https://arxiv.org/pdf/2412.00686v2.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":"lvlm-count-enhancing-the-counting-ability-of","repo_url":"https://github.com/mrghofrani/lvlm-count","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"object-recognition","task_name":"Object Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2412.00686","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.00686"}},"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/mrghofrani/lvlm-count","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"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":"cc8fe2e6f608cc26","entry":"calculate_area","repo":"mrghofrani/lvlm-count","repo_kind":"official","path":"src/image_divider.py","file_url":"https://github.com/mrghofrani/lvlm-count/blob/HEAD/src/image_divider.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cc8fe2e6f608cc26"}},{"code_sha256_prefix":"be07bdaad69d1de7","entry":"crop_image_from_bounding_boxes","repo":"mrghofrani/lvlm-count","repo_kind":"official","path":"src/image_divider.py","file_url":"https://github.com/mrghofrani/lvlm-count/blob/HEAD/src/image_divider.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"be07bdaad69d1de7"}},{"code_sha256_prefix":"6c257111a8dbdccb","entry":"merge_boxes","repo":"mrghofrani/lvlm-count","repo_kind":"official","path":"src/image_divider.py","file_url":"https://github.com/mrghofrani/lvlm-count/blob/HEAD/src/image_divider.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6c257111a8dbdccb"}},{"code_sha256_prefix":"74f3044b35903eab","entry":"object_counter","repo":"mrghofrani/lvlm-count","repo_kind":"official","path":"extract_phrase_by_llm_and_count_the_masks_extracted_by_groundingdino/eval_emoji.py","file_url":"https://github.com/mrghofrani/lvlm-count/blob/HEAD/extract_phrase_by_llm_and_count_the_masks_extracted_by_groundingdino/eval_emoji.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"74f3044b35903eab"}},{"code_sha256_prefix":"0d380c727e43fa76","entry":"object_counter","repo":"mrghofrani/lvlm-count","repo_kind":"official","path":"extract_phrase_by_llm_and_count_the_masks_extracted_by_groundingdino/eval_fsc147.py","file_url":"https://github.com/mrghofrani/lvlm-count/blob/HEAD/extract_phrase_by_llm_and_count_the_masks_extracted_by_groundingdino/eval_fsc147.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0d380c727e43fa76"}},{"code_sha256_prefix":"91e97a59b3a61502","entry":"phrase_singulaizer","repo":"mrghofrani/lvlm-count","repo_kind":"official","path":"extract_phrase_by_llm_and_count_the_masks_extracted_by_groundingdino/eval_fsc147.py","file_url":"https://github.com/mrghofrani/lvlm-count/blob/HEAD/extract_phrase_by_llm_and_count_the_masks_extracted_by_groundingdino/eval_fsc147.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"91e97a59b3a61502"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}