{"id":"W4410730174","doi":"10.1007/978-3-031-91585-7_21","title":"A Bottom-Up Approach to Class-Agnostic Image Segmentation","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; Simon Fraser University","funders":"","keywords":"Computer science; Top-down and bottom-up design; Class (philosophy); Segmentation; Image segmentation; Artificial intelligence; Computer vision; Image (mathematics); Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001022676,0.001776727,0.002343889,0.00293478,0.001578138,0.004012694,0.005492907,0.002568124,0.01133061],"category_scores_gemma":[0.002468198,0.001781797,0.00273997,0.002805974,0.001430911,0.002615589,0.004923405,0.003864435,0.008546133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001220628,"about_ca_system_score_gemma":0.001643872,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004113571,"about_ca_topic_score_gemma":0.008639459,"domain_scores_codex":[0.9978337,0.0001948557,0.0001171062,0.0006193524,0.0009557506,0.00027927],"domain_scores_gemma":[0.9978595,0.0004366463,0.00009306271,0.0009881842,0.0005279435,0.00009470076],"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":[0.0002318774,0.0002148011,0.000493975,0.0002969813,0.000137954,0.0002266295,0.0001607409,0.02304814,0.09352028,0.02810363,0.01934823,0.8342168],"study_design_scores_gemma":[0.00003468275,0.0001408256,0.001265389,0.00009285456,0.0001716154,0.000991533,0.0001402961,0.7363139,0.1039013,0.1034624,0.05337268,0.0001125517],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001174838,0.0001974992,0.9917096,0.00008551042,0.00005289445,0.00006877459,0.00009867115,0.004134738,0.002477478],"genre_scores_gemma":[0.03503848,0.0003584187,0.9516976,0.0003810947,0.0001156934,0.00009999856,0.0007289642,0.001621128,0.009958697],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01133061,"threshold_uncertainty_score":0.03790462,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01614573989717177,"score_gpt":0.2815749654816712,"score_spread":0.2654292255844994,"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."}}