{"id":"W4245153788","doi":"10.21203/rs.3.rs-253336/v1","title":"Weakly Supervised Underwater Fish Segmentation Using Affinity LCFCN","year":2021,"lang":"en","type":"preprint","venue":"Research Square","topic":"Water Quality Monitoring Technologies","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Segmentation; Computer science; Artificial intelligence; Pixel; Underwater; Convolutional neural network; Annotation; Point (geometry); Pattern recognition (psychology); Mathematics; Geography","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001855886,0.0003249305,0.0003457886,0.0002212936,0.0004192501,0.0005941347,0.001093157,0.000572653,0.001394609],"category_scores_gemma":[0.0003762831,0.0003185585,0.0001593262,0.0005642046,0.0005391494,0.0003203936,0.007824836,0.00182622,0.0002802486],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001893361,"about_ca_system_score_gemma":0.0001312735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005030949,"about_ca_topic_score_gemma":0.0004793252,"domain_scores_codex":[0.9947501,0.0009862521,0.0004036659,0.001051398,0.00189641,0.0009121078],"domain_scores_gemma":[0.9980934,0.0002100435,0.00009158707,0.001338363,0.0001066207,0.0001600334],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001517414,0.001632201,0.4059897,0.003272067,0.0003070823,0.0006713326,0.01179477,0.03821265,0.5070502,0.00008103505,0.01384554,0.01699172],"study_design_scores_gemma":[0.0009626583,0.0003794598,0.1711411,0.001806069,0.00006819628,0.00002258406,0.01809043,0.008251315,0.7827863,0.0120619,0.002467263,0.001962823],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9956064,0.00004954707,0.0005555105,0.001470727,0.0003687844,0.0008254751,0.00005596571,0.0003346154,0.0007329727],"genre_scores_gemma":[0.9843543,0.0001187832,0.01452057,0.00003195203,0.000152042,0.0001329565,0.0002112574,0.00005643859,0.0004216949],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2757361,"threshold_uncertainty_score":0.9999266,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1859039621011201,"score_gpt":0.404624938853755,"score_spread":0.2187209767526349,"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."}}