{"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/talisman-targeted-active-learning-for-object","title":"TALISMAN: Targeted Active Learning for Object Detection with Rare Classes and Slices using Submodular Mutual Information","arxiv_id":"2112.00166","date":"2021-11-30","proceeding":null,"authors":["Suraj Kothawade","Saikat Ghosh","Sumit Shekhar","Yu Xiang","Rishabh Iyer"],"abstract":"Deep neural networks based object detectors have shown great success in a variety of domains like autonomous vehicles, biomedical imaging, etc. It is known that their success depends on a large amount of data from the domain of interest. While deep models often perform well in terms of overall accuracy, they often struggle in performance on rare yet critical data slices. For example, data slices like \"motorcycle at night\" or \"bicycle at night\" are often rare but very critical slices for self-driving applications and false negatives on such rare slices could result in ill-fated failures and accidents. Active learning (AL) is a well-known paradigm to incrementally and adaptively build training datasets with a human in the loop. However, current AL based acquisition functions are not well-equipped to tackle real-world datasets with rare slices, since they are based on uncertainty scores or global descriptors of the image. We propose TALISMAN, a novel framework for Targeted Active Learning or object detectIon with rare slices using Submodular MutuAl iNformation. Our method uses the submodular mutual information functions instantiated using features of the region of interest (RoI) to efficiently target and acquire data points with rare slices. We evaluate our framework on the standard PASCAL VOC07+12 and BDD100K, a real-world self-driving dataset. We observe that TALISMAN outperforms other methods by in terms of average precision on rare slices, and in terms of mAP.","url_abs":"https://arxiv.org/abs/2112.00166v2","url_pdf":"https://arxiv.org/pdf/2112.00166v2.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":"talisman-targeted-active-learning-for-object","repo_url":"https://github.com/surajkothawade/talisman","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"active-learning","task_name":"Active Learning"},{"task_slug":"autonomous-vehicles","task_name":"Autonomous Vehicles"},{"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=2112.00166","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.00166"}},"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/surajkothawade/talisman","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":12},"by_repo_kind":{"official":{"samples":12,"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":"85ed5296deff1e84","entry":"compute_queryImage_kernel","repo":"surajkothawade/talisman","repo_kind":"official","path":"talisman/strategies/active_learning_utils/compute_kernel.py","file_url":"https://github.com/surajkothawade/talisman/blob/HEAD/talisman/strategies/active_learning_utils/compute_kernel.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":"85ed5296deff1e84"}},{"code_sha256_prefix":"84039b965f3086e4","entry":"compute_queryQuery_kernel","repo":"surajkothawade/talisman","repo_kind":"official","path":"talisman/strategies/active_learning_utils/compute_kernel.py","file_url":"https://github.com/surajkothawade/talisman/blob/HEAD/talisman/strategies/active_learning_utils/compute_kernel.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":"84039b965f3086e4"}},{"code_sha256_prefix":"6e50f9ceb4249e69","entry":"create_custom_dataset","repo":"surajkothawade/talisman","repo_kind":"official","path":"talisman/strategies/active_learning_utils/custom_dataset.py","file_url":"https://github.com/surajkothawade/talisman/blob/HEAD/talisman/strategies/active_learning_utils/custom_dataset.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":"6e50f9ceb4249e69"}},{"code_sha256_prefix":"8f021d473ea660b6","entry":"extract_proposal_features","repo":"surajkothawade/talisman","repo_kind":"official","path":"talisman/strategies/active_learning_utils/extract_features.py","file_url":"https://github.com/surajkothawade/talisman/blob/HEAD/talisman/strategies/active_learning_utils/extract_features.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":"8f021d473ea660b6"}},{"code_sha256_prefix":"391d1d55a2451546","entry":"furthest_first","repo":"surajkothawade/talisman","repo_kind":"official","path":"talisman/strategies/active_learning_utils/furthest_first_coreset.py","file_url":"https://github.com/surajkothawade/talisman/blob/HEAD/talisman/strategies/active_learning_utils/furthest_first_coreset.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":"391d1d55a2451546"}},{"code_sha256_prefix":"9dc8eb192c8a42dd","entry":"get_class_statistics","repo":"surajkothawade/talisman","repo_kind":"official","path":"talisman/strategies/active_learning_utils/custom_dataset.py","file_url":"https://github.com/surajkothawade/talisman/blob/HEAD/talisman/strategies/active_learning_utils/custom_dataset.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":"9dc8eb192c8a42dd"}},{"code_sha256_prefix":"a60fc8e6d28f3903","entry":"init_centers","repo":"surajkothawade/talisman","repo_kind":"official","path":"talisman/strategies/active_learning_utils/clustering.py","file_url":"https://github.com/surajkothawade/talisman/blob/HEAD/talisman/strategies/active_learning_utils/clustering.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":"a60fc8e6d28f3903"}},{"code_sha256_prefix":"1e706ca592829e24","entry":"l2_normalize","repo":"surajkothawade/talisman","repo_kind":"official","path":"talisman/strategies/active_learning_utils/compute_kernel.py","file_url":"https://github.com/surajkothawade/talisman/blob/HEAD/talisman/strategies/active_learning_utils/compute_kernel.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":"1e706ca592829e24"}},{"code_sha256_prefix":"8ff99a6bd2ebf598","entry":"ordered_yaml_dump","repo":"surajkothawade/talisman","repo_kind":"official","path":".dev_scripts/gather_models.py","file_url":"https://github.com/surajkothawade/talisman/blob/HEAD/.dev_scripts/gather_models.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":"8ff99a6bd2ebf598"}},{"code_sha256_prefix":"bcc3b99e8d9ea31d","entry":"prepare_val_file","repo":"surajkothawade/talisman","repo_kind":"official","path":"talisman/strategies/active_learning_utils/custom_dataset.py","file_url":"https://github.com/surajkothawade/talisman/blob/HEAD/talisman/strategies/active_learning_utils/custom_dataset.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":"bcc3b99e8d9ea31d"}},{"code_sha256_prefix":"138e112e22b0314e","entry":"process_checkpoint","repo":"surajkothawade/talisman","repo_kind":"official","path":".dev_scripts/gather_models.py","file_url":"https://github.com/surajkothawade/talisman/blob/HEAD/.dev_scripts/gather_models.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":"138e112e22b0314e"}},{"code_sha256_prefix":"6466cc7ecba5e5d0","entry":"select_top_k_proposals","repo":"surajkothawade/talisman","repo_kind":"official","path":"talisman/strategies/active_learning_utils/extract_features.py","file_url":"https://github.com/surajkothawade/talisman/blob/HEAD/talisman/strategies/active_learning_utils/extract_features.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":"6466cc7ecba5e5d0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}