{"id":"W4366608144","doi":"10.1016/j.compag.2023.107839","title":"A semi-supervised generative adversarial network for amodal instance segmentation of piglets in farrowing pens","year":2023,"lang":"en","type":"article","venue":"Computers and Electronics in Agriculture","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"City University of Hong Kong","keywords":"Amodal perception; Artificial intelligence; Segmentation; Intersection (aeronautics); Computer science; Pattern recognition (psychology); Machine learning; Computer vision; Engineering","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":[0.0005327342,0.0001373051,0.0002489026,0.00008907382,0.00007888958,0.00005714982,0.0002600022,0.0000897126,1.985792e-7],"category_scores_gemma":[0.00001793488,0.0001130202,0.00005257661,0.0009432838,0.00001851862,0.0001898367,0.00008871685,0.0001807702,2.815614e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007702009,"about_ca_system_score_gemma":0.00005967407,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003191272,"about_ca_topic_score_gemma":0.0004990951,"domain_scores_codex":[0.9987689,0.0001176441,0.0002516902,0.0003432908,0.000131065,0.0003874626],"domain_scores_gemma":[0.9994951,0.0002079495,0.0000817598,0.0001286723,0.00005280512,0.00003365812],"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":[0.0001848521,0.0002464576,0.04028331,0.0003099643,0.0001673154,0.00009238152,0.02305248,0.536273,0.05620397,0.07005709,0.009863551,0.2632656],"study_design_scores_gemma":[0.005400398,0.000614358,0.05456041,0.0003526094,0.00001444904,0.0000266703,0.0005949018,0.9041045,0.005897822,0.0243834,0.003253031,0.0007974373],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4902344,0.0009305734,0.5073904,0.0004616315,0.0004797171,0.0003961324,0.000003631648,0.00006244928,0.00004099532],"genre_scores_gemma":[0.8872191,0.0004086393,0.1118627,0.0001874542,0.0002072569,0.00004604164,0.00003903458,0.000008241316,0.00002158016],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3969846,"threshold_uncertainty_score":0.460883,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01642659911444148,"score_gpt":0.2661724265751489,"score_spread":0.2497458274607074,"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."}}