{"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/weakly-supervised-residual-evidential","title":"Weakly-Supervised Residual Evidential Learning for Multi-Instance Uncertainty Estimation","arxiv_id":"2405.04405","date":"2024-05-07","proceeding":null,"authors":["Pei Liu","Luping Ji"],"abstract":"Uncertainty estimation (UE), as an effective means of quantifying predictive uncertainty, is crucial for safe and reliable decision-making, especially in high-risk scenarios. Existing UE schemes usually assume that there are completely-labeled samples to support fully-supervised learning. In practice, however, many UE tasks often have no sufficiently-labeled data to use, such as the Multiple Instance Learning (MIL) with only weak instance annotations. To bridge this gap, this paper, for the first time, addresses the weakly-supervised issue of Multi-Instance UE (MIUE) and proposes a new baseline scheme, Multi-Instance Residual Evidential Learning (MIREL). Particularly, at the fine-grained instance UE with only weak supervision, we derive a multi-instance residual operator through the Fundamental Theorem of Symmetric Functions. On this operator derivation, we further propose MIREL to jointly model the high-order predictive distribution at bag and instance levels for MIUE. Extensive experiments empirically demonstrate that our MIREL not only could often make existing MIL networks perform better in MIUE, but also could surpass representative UE methods by large margins, especially in instance-level UE tasks. Our source code is available at https://github.com/liupei101/MIREL.","url_abs":"https://arxiv.org/abs/2405.04405v2","url_pdf":"https://arxiv.org/pdf/2405.04405v2.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":"weakly-supervised-residual-evidential","repo_url":"https://github.com/liupei101/mirel","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"multiple-instance-learning","task_name":"Multiple Instance Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.04405","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.04405"}},"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":"deterministic:regex_extraction","url":"https://github.com/liupei101/MIREL","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/liupei101/mirel","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":6,"unverified":5},"by_repo_kind":{"official":{"samples":11,"ran":6,"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":"af34b926cbeb626c","entry":"aggregate_instance_evidence","repo":"liupei101/MIREL","repo_kind":"official","path":"loss/loss_edl.py","file_url":"https://github.com/liupei101/MIREL/blob/HEAD/loss/loss_edl.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"af34b926cbeb626c"}},{"code_sha256_prefix":"ddba7773fd3d51f7","entry":"exp_evidence","repo":"liupei101/MIREL","repo_kind":"official","path":"model/layer_utils.py","file_url":"https://github.com/liupei101/MIREL/blob/HEAD/model/layer_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ddba7773fd3d51f7"}},{"code_sha256_prefix":"b810113372d69a75","entry":"kl_divergence","repo":"liupei101/MIREL","repo_kind":"official","path":"loss/loss_edl.py","file_url":"https://github.com/liupei101/MIREL/blob/HEAD/loss/loss_edl.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b810113372d69a75"}},{"code_sha256_prefix":"9e753dca3a11c335","entry":"loss_reg_l1","repo":"liupei101/MIREL","repo_kind":"official","path":"loss/utils.py","file_url":"https://github.com/liupei101/MIREL/blob/HEAD/loss/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9e753dca3a11c335"}},{"code_sha256_prefix":"efecc687b786a0cc","entry":"relu_evidence","repo":"liupei101/MIREL","repo_kind":"official","path":"model/layer_utils.py","file_url":"https://github.com/liupei101/MIREL/blob/HEAD/model/layer_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"efecc687b786a0cc"}},{"code_sha256_prefix":"f8059bd409d4bdf3","entry":"softplus_evidence","repo":"liupei101/MIREL","repo_kind":"official","path":"model/layer_utils.py","file_url":"https://github.com/liupei101/MIREL/blob/HEAD/model/layer_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f8059bd409d4bdf3"}},{"code_sha256_prefix":"74911f7aa32bebb9","entry":"ABMIL","repo":"liupei101/mirel","repo_kind":"official","path":"model/evmil.py","file_url":"https://github.com/liupei101/mirel/blob/HEAD/model/evmil.py","link_basis":"first_harvest_node","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":"74911f7aa32bebb9"}},{"code_sha256_prefix":"d257066e06719d0b","entry":"Deep_ABMIL","repo":"liupei101/MIREL","repo_kind":"official","path":"model/model_utils.py","file_url":"https://github.com/liupei101/MIREL/blob/HEAD/model/model_utils.py","link_basis":"first_harvest_node","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":"d257066e06719d0b"}},{"code_sha256_prefix":"802a0dfcb54377e6","entry":"Deep_MIL","repo":"liupei101/MIREL","repo_kind":"official","path":"model/model_utils.py","file_url":"https://github.com/liupei101/MIREL/blob/HEAD/model/model_utils.py","link_basis":"first_harvest_node","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":"802a0dfcb54377e6"}},{"code_sha256_prefix":"6ed66871680b63db","entry":"load_loss","repo":"liupei101/MIREL","repo_kind":"official","path":"loss/utils.py","file_url":"https://github.com/liupei101/MIREL/blob/HEAD/loss/utils.py","link_basis":"first_harvest_node","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":"6ed66871680b63db"}},{"code_sha256_prefix":"6640364ac6052908","entry":"load_model","repo":"liupei101/MIREL","repo_kind":"official","path":"model/model_utils.py","file_url":"https://github.com/liupei101/MIREL/blob/HEAD/model/model_utils.py","link_basis":"first_harvest_node","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":"6640364ac6052908"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}