{"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/cap2det-learning-to-amplify-weak-caption","title":"Cap2Det: Learning to Amplify Weak Caption Supervision for Object Detection","arxiv_id":"1907.10164","date":"2019-07-23","proceeding":"ICCV 2019 10","authors":["Keren Ye","Mingda Zhang","Adriana Kovashka","Wei Li","Danfeng Qin","Jesse Berent"],"abstract":"Learning to localize and name object instances is a fundamental problem in vision, but state-of-the-art approaches rely on expensive bounding box supervision. While weakly supervised detection (WSOD) methods relax the need for boxes to that of image-level annotations, even cheaper supervision is naturally available in the form of unstructured textual descriptions that users may freely provide when uploading image content. However, straightforward approaches to using such data for WSOD wastefully discard captions that do not exactly match object names. Instead, we show how to squeeze the most information out of these captions by training a text-only classifier that generalizes beyond dataset boundaries. Our discovery provides an opportunity for learning detection models from noisy but more abundant and freely-available caption data. We also validate our model on three classic object detection benchmarks and achieve state-of-the-art WSOD performance. Our code is available at https://github.com/yekeren/Cap2Det.","url_abs":"https://arxiv.org/abs/1907.10164v3","url_pdf":"https://arxiv.org/pdf/1907.10164v3.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":"cap2det-learning-to-amplify-weak-caption","repo_url":"https://github.com/yekeren/Cap2Det","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1907.10164","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.10164"}},"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/yekeren/Cap2Det","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":11},"by_repo_kind":{"official":{"samples":11,"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":"6ef03b0292d06b27","entry":"area","repo":"yekeren/Cap2Det","repo_kind":"official","path":"core/box_utils.py","file_url":"https://github.com/yekeren/Cap2Det/blob/HEAD/core/box_utils.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":"6ef03b0292d06b27"}},{"code_sha256_prefix":"3a41de440a471316","entry":"convert_to_heatmap","repo":"yekeren/Cap2Det","repo_kind":"official","path":"core/plotlib.py","file_url":"https://github.com/yekeren/Cap2Det/blob/HEAD/core/plotlib.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":"3a41de440a471316"}},{"code_sha256_prefix":"9f0bf8e77b1abe07","entry":"deprecated","repo":"yekeren/Cap2Det","repo_kind":"official","path":"core/utils.py","file_url":"https://github.com/yekeren/Cap2Det/blob/HEAD/core/utils.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":"9f0bf8e77b1abe07"}},{"code_sha256_prefix":"f8f60a78c2de43e1","entry":"draw_caption","repo":"yekeren/Cap2Det","repo_kind":"official","path":"core/plotlib.py","file_url":"https://github.com/yekeren/Cap2Det/blob/HEAD/core/plotlib.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":"f8f60a78c2de43e1"}},{"code_sha256_prefix":"b6c57a7a8feef42a","entry":"flip_left_right","repo":"yekeren/Cap2Det","repo_kind":"official","path":"core/box_utils.py","file_url":"https://github.com/yekeren/Cap2Det/blob/HEAD/core/box_utils.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":"b6c57a7a8feef42a"}},{"code_sha256_prefix":"4c6055237031fde4","entry":"get_best_model_checkpoint","repo":"yekeren/Cap2Det","repo_kind":"official","path":"core/training_utils.py","file_url":"https://github.com/yekeren/Cap2Det/blob/HEAD/core/training_utils.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":"4c6055237031fde4"}},{"code_sha256_prefix":"34e949d7493fefae","entry":"get_tensor_shape","repo":"yekeren/Cap2Det","repo_kind":"official","path":"core/utils.py","file_url":"https://github.com/yekeren/Cap2Det/blob/HEAD/core/utils.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":"34e949d7493fefae"}},{"code_sha256_prefix":"9d288a679f2437bf","entry":"masked_maximum","repo":"yekeren/Cap2Det","repo_kind":"official","path":"core/utils.py","file_url":"https://github.com/yekeren/Cap2Det/blob/HEAD/core/utils.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":"9d288a679f2437bf"}},{"code_sha256_prefix":"3b9582df579e4c57","entry":"preprocess_func","repo":"yekeren/Cap2Det","repo_kind":"official","path":"core/preprocess.py","file_url":"https://github.com/yekeren/Cap2Det/blob/HEAD/core/preprocess.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":"3b9582df579e4c57"}},{"code_sha256_prefix":"54265b15b32a3560","entry":"random_crop","repo":"yekeren/Cap2Det","repo_kind":"official","path":"core/preprocess.py","file_url":"https://github.com/yekeren/Cap2Det/blob/HEAD/core/preprocess.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":"54265b15b32a3560"}},{"code_sha256_prefix":"57546be4901a2405","entry":"scale_to_new_size","repo":"yekeren/Cap2Det","repo_kind":"official","path":"core/box_utils.py","file_url":"https://github.com/yekeren/Cap2Det/blob/HEAD/core/box_utils.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":"57546be4901a2405"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}