{"id":"W2925338335","doi":"10.1109/iccv.2019.00858","title":"BAE-NET: Branched Autoencoder for Shape Co-Segmentation","year":2019,"lang":"en","type":"preprint","venue":"","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Autoencoder; Segmentation; Artificial intelligence; Net (polyhedron); Code (set theory); Computer science; Pattern recognition (psychology); Representation (politics); Feature learning; Ground truth; Convolutional neural network; Feature (linguistics); Deep learning; Point (geometry); Artificial neural network; Mathematics; Geometry","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001402753,0.0002595716,0.0003577539,0.0001368115,0.00003454164,0.00008749336,0.0001928297,0.0002659153,0.0006444801],"category_scores_gemma":[0.00001016768,0.0002540649,0.000263708,0.00005524483,0.00000868006,0.00005156162,0.00004855175,0.0002407351,0.0002119571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000798999,"about_ca_system_score_gemma":0.00003154766,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002431887,"about_ca_topic_score_gemma":0.00001144211,"domain_scores_codex":[0.9989504,0.0000108709,0.0003113871,0.0003331588,0.0001615618,0.0002326724],"domain_scores_gemma":[0.9994408,0.00004796761,0.00004750127,0.0003483858,0.00006179069,0.00005356573],"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":[0.000003309758,0.000009491744,0.00009650268,0.0003968941,0.0002023163,2.524389e-7,0.0001536808,0.9849988,0.0009241908,0.00002133546,0.006758685,0.006434522],"study_design_scores_gemma":[0.0002646378,0.00000792265,0.00006181127,0.00005199875,0.0001095256,2.83307e-7,0.00004125321,0.9961112,0.001864386,0.0004782238,0.0006944487,0.000314364],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01854779,0.0003199722,0.9700302,0.00008595761,0.0005900001,0.0004323647,0.00009173474,0.0006161684,0.009285792],"genre_scores_gemma":[0.9636268,0.0001399931,0.03045442,0.0001483715,0.0002634273,0.0001615303,0.0008871983,0.00009493281,0.004223302],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.945079,"threshold_uncertainty_score":0.9999912,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02398305114019602,"score_gpt":0.2739904483158915,"score_spread":0.2500073971756955,"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."}}