{"id":"W4413945294","doi":"10.1109/icra55743.2025.11127615","title":"Promi: an Efficient Prototype-Mixture Baseline for Few-Shot Segmentation with Bounding-Box Annotations","year":2025,"lang":"en","type":"article","venue":"","topic":"Image Processing and 3D Reconstruction","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University; Thales (Canada)","funders":"","keywords":"Computer science; Baseline (sea); Minimum bounding box; Shot (pellet); Bounding overwatch; Segmentation; Artificial intelligence; Computer vision; Computer graphics (images); Image (mathematics); Geology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002846216,0.0001087951,0.00009446909,0.0001459765,0.0003782526,0.0003481267,0.0002050879,0.00004267709,0.000007338221],"category_scores_gemma":[0.00003126715,0.00008123246,0.0000256665,0.0004799763,0.00004279402,0.0004139371,0.00002271164,0.00007246323,0.000003631077],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004222748,"about_ca_system_score_gemma":0.000290026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000814976,"about_ca_topic_score_gemma":0.00002686733,"domain_scores_codex":[0.9991445,0.00003651455,0.000167082,0.0003454133,0.0001316081,0.0001748921],"domain_scores_gemma":[0.9993594,0.00003732473,0.00007036321,0.0002215458,0.0002678914,0.00004350999],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004205966,0.001037067,0.00180758,0.0008091822,0.0001175586,0.000005135007,0.004278553,0.01122304,0.02403663,0.09882839,0.003337405,0.8540989],"study_design_scores_gemma":[0.001241397,0.0004302169,0.0003220518,0.0001168912,0.0000306763,0.00002713075,0.0003123862,0.922812,0.07017925,0.002503632,0.001770874,0.0002534555],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01382965,0.00002334997,0.9818704,0.001228632,0.0002985957,0.001113545,0.000003299786,0.0002332453,0.001399311],"genre_scores_gemma":[0.2851464,7.699315e-7,0.7120318,0.0003571341,0.00005784937,0.0005112181,0.0000342811,0.000007773776,0.001852709],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.911589,"threshold_uncertainty_score":0.3356993,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01267345089137351,"score_gpt":0.2891095351494586,"score_spread":0.2764360842580851,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}