{"id":"W4412873526","doi":"10.2139/ssrn.5358561","title":"Dynamic Mutual Adversarial Learning for Semi-Supervised Semantic Segmentation of Underwater Images with Limited and Noisy Annotations","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"","keywords":"Segmentation; Adversarial system; Computer science; Underwater; Artificial intelligence; Computer vision; Pattern recognition (psychology); Machine learning; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001980394,0.001188835,0.001749263,0.001046928,0.0004841815,0.001150478,0.00234237,0.002285865,0.001684681],"category_scores_gemma":[0.004978598,0.00120127,0.001347495,0.001054004,0.001600408,0.001934294,0.002955782,0.002165135,0.0006692589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009766401,"about_ca_system_score_gemma":0.001124984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003730533,"about_ca_topic_score_gemma":0.004167422,"domain_scores_codex":[0.9989962,0.0003202053,0.00004218666,0.0003265289,0.0001869801,0.0001279237],"domain_scores_gemma":[0.9977499,0.001434174,0.0002661432,0.0002812749,0.0001836862,0.00008481369],"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":[0.0004646164,0.00009958913,0.0005375418,0.0001669164,0.0001054968,0.000156466,0.0001906346,0.8544925,0.01168796,0.008487799,0.002057988,0.1215525],"study_design_scores_gemma":[0.000003233391,0.00001499979,0.00008639494,0.00000584309,0.000005030458,0.00001814181,0.000006664801,0.9954351,0.001262637,0.003003416,0.000154258,0.000004397697],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02085288,0.0002054593,0.9770525,0.0001677063,0.00002698769,0.00003901031,0.0001338403,0.0007866863,0.0007349308],"genre_scores_gemma":[0.6912494,0.0003914864,0.2989514,0.0003136825,0.0001429912,0.0002528351,0.001323024,0.00059488,0.006780419],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003730533,"threshold_uncertainty_score":0.01047343,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007017174008908051,"score_gpt":0.2579206903466361,"score_spread":0.2509035163377281,"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."}}