{"id":"W4392856651","doi":"10.3390/jimaging10030071","title":"FishSegSSL: A Semi-Supervised Semantic Segmentation Framework for Fish-Eye Images","year":2024,"lang":"en","type":"article","venue":"Journal of Imaging","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Mitacs","keywords":"Computer science; Artificial intelligence; Segmentation; Thresholding; Computer vision; Benchmark (surveying); Perspective (graphical); Image segmentation; Supervised learning; Pattern recognition (psychology); Image (mathematics); Artificial neural network","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":[],"consensus_categories":[],"category_scores_codex":[0.0002835737,0.0001213053,0.0001622823,0.0001676818,0.0001193922,0.0003993878,0.0005207621,0.00002565101,0.000008403203],"category_scores_gemma":[0.00009453562,0.000106182,0.0001486898,0.0004636082,0.00002792136,0.001371932,0.00008112736,0.0002709923,0.000008859221],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007274143,"about_ca_system_score_gemma":0.00006528561,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.673119e-7,"about_ca_topic_score_gemma":3.43289e-7,"domain_scores_codex":[0.9988932,0.00003007929,0.0003923477,0.0002163461,0.0002406614,0.0002273582],"domain_scores_gemma":[0.9988685,0.0004703593,0.0001790245,0.000233509,0.0001644878,0.00008408605],"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":[0.00003697577,0.0001405556,0.001708394,0.0003979811,0.0001714006,0.000293042,0.002492618,0.007848125,0.09904417,0.03896226,0.06686876,0.7820357],"study_design_scores_gemma":[0.0006139132,0.0001069577,0.001105099,0.0009830032,0.00009232046,0.0005043413,0.0002220345,0.7510681,0.03640492,0.1883456,0.02013464,0.0004191126],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003496552,0.001039737,0.9740084,0.02043571,0.0006624943,0.0001803611,0.000004543474,0.0001027509,0.00006940692],"genre_scores_gemma":[0.3343338,0.0001457243,0.6633413,0.001439395,0.0005972425,0.00002214607,0.000002023456,0.00002463893,0.00009375634],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7816166,"threshold_uncertainty_score":0.4329975,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01631232563242381,"score_gpt":0.3152401816898467,"score_spread":0.2989278560574229,"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."}}