{"id":"W2794772564","doi":"10.48550/arxiv.1803.09569","title":"On Regularized Losses for Weakly-supervised CNN Segmentation","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure; University of Waterloo","funders":"","keywords":"Regularization (linguistics); Segmentation; Inference; Computer science; CRFS; Artificial intelligence; Minification; Graph; Machine learning; Pattern recognition (psychology); Algorithm; Conditional random field; Theoretical computer science","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"],"consensus_categories":[],"category_scores_codex":[0.0001299237,0.0003025146,0.0002692695,0.0001777089,0.0002838878,0.0001045545,0.001617028,0.0002129733,0.00002532526],"category_scores_gemma":[0.00003897147,0.0003501162,0.0001950135,0.0005125601,0.0001193068,0.0003396585,0.0008727855,0.0002642582,0.0001309856],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002125186,"about_ca_system_score_gemma":0.0001049282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009333712,"about_ca_topic_score_gemma":0.000009407644,"domain_scores_codex":[0.9980358,0.00007985967,0.0002012801,0.001254531,0.00009580594,0.0003326971],"domain_scores_gemma":[0.9975945,0.0003023375,0.0002682685,0.001476949,0.000226004,0.0001319064],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001915231,0.0002171147,0.0001025961,0.0001060142,0.0001151718,0.00002972979,0.0001674284,0.2306698,0.00259202,0.7575893,0.004943099,0.003276159],"study_design_scores_gemma":[0.0007347074,0.0001237854,0.00010069,0.00006080158,0.0000473304,0.000001269543,0.00001591535,0.627947,0.003278377,0.366517,0.0007729456,0.0004001489],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1099819,0.00001141828,0.8871983,0.0002754544,0.0004348098,0.0009918942,0.00002385788,0.0003316122,0.0007508324],"genre_scores_gemma":[0.9105728,0.00008405303,0.08616334,0.0003666327,0.0002072527,0.00002596781,0.00009492658,0.00003368213,0.00245139],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8010349,"threshold_uncertainty_score":0.9998951,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07747897837039533,"score_gpt":0.2227127744818481,"score_spread":0.1452337961114528,"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."}}