{"id":"W4404889959","doi":"10.1007/978-3-031-78347-0_10","title":"Task Consistent Prototype Learning for Incremental Few-Shot Semantic Segmentation","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Shot (pellet); Task (project management); Segmentation; Artificial intelligence; Natural language processing","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001159932,0.0005024513,0.0004452214,0.0008014213,0.00043745,0.001101695,0.001400696,0.0002258089,0.00003532866],"category_scores_gemma":[0.0001120737,0.0004794602,0.0001901668,0.0005273307,0.0003749306,0.0005387078,0.0007335401,0.0008834704,0.0001357755],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000427512,"about_ca_system_score_gemma":0.0004497405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000134425,"about_ca_topic_score_gemma":0.00003321138,"domain_scores_codex":[0.9962429,0.00004684137,0.0006018584,0.001522369,0.0009605922,0.0006254034],"domain_scores_gemma":[0.9982466,0.0004540927,0.0003087405,0.0005878781,0.0002384031,0.0001642542],"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":[0.00005136099,0.00005978612,0.0001235712,0.0004824717,0.00008303848,0.0001289421,0.004318103,0.102496,0.00429692,0.08505522,0.00006900752,0.8028355],"study_design_scores_gemma":[0.0005173548,0.0005615643,0.00004194403,0.000630849,0.00002742413,0.00007462136,0.000003587714,0.9334283,0.001407887,0.05388621,0.008691721,0.0007285159],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00009181231,0.0004121782,0.9904312,0.0007484712,0.00183381,0.001640966,0.000003828409,0.000306512,0.004531225],"genre_scores_gemma":[0.4158787,0.00005541478,0.5761847,0.0020358,0.0006900023,0.0002217334,0.00006593682,0.0001161537,0.004751531],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8309323,"threshold_uncertainty_score":0.9999353,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03053417545826976,"score_gpt":0.2784786636380164,"score_spread":0.2479444881797466,"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."}}