{"id":"W4403780071","doi":"10.48550/arxiv.2409.13687","title":"A Bottom-Up Approach to Class-Agnostic Image Segmentation","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Digital Imaging for Blood Diseases","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Class (philosophy); Segmentation; Computer science; Image (mathematics); Computer vision; Artificial intelligence; Top-down and bottom-up design; Geology; Software engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001622942,0.001416457,0.001519764,0.001079162,0.0008036681,0.002063042,0.003659492,0.002693201,0.004067301],"category_scores_gemma":[0.003590866,0.0009202207,0.001286022,0.0009836082,0.001965401,0.002821918,0.003324445,0.002879911,0.001768455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001268137,"about_ca_system_score_gemma":0.001301419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002237692,"about_ca_topic_score_gemma":0.003947189,"domain_scores_codex":[0.9987966,0.0002585756,0.00004516355,0.0004100993,0.0003457736,0.0001437956],"domain_scores_gemma":[0.9984168,0.0005117495,0.0001592556,0.00048642,0.000314468,0.0001113256],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001997813,0.0002150425,0.001207868,0.0002551196,0.0001519526,0.0002896558,0.0002958109,0.5012223,0.05763352,0.06739348,0.009103513,0.362032],"study_design_scores_gemma":[0.000007249298,0.00005030105,0.0002002455,0.00001286562,0.00001853307,0.00009037298,0.00001403289,0.9606038,0.007150578,0.02932855,0.002508765,0.00001467807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003440888,0.0001018098,0.9943119,0.0001402627,0.00001575755,0.00003784203,0.00004586949,0.0007132875,0.001192429],"genre_scores_gemma":[0.2234044,0.0003655695,0.766092,0.0007736468,0.0001748685,0.0002046991,0.0005189001,0.0008991606,0.007566761],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004067301,"threshold_uncertainty_score":0.01360649,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05059498197141481,"score_gpt":0.2012697275964091,"score_spread":0.1506747456249943,"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."}}