{"id":"W4402727877","doi":"10.1109/cvpr52733.2024.00322","title":"ECLIPSE: Efficient Continual Learning in Panoptic Segmentation with Visual Prompt Tuning","year":2024,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; Korea Advanced Institute of Science and Technology","keywords":"Eclipse; Panopticon; Computer science; Segmentation; Artificial intelligence; Computer vision; Image segmentation; Astronomy","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":[],"consensus_categories":[],"category_scores_codex":[0.0004789749,0.0001263195,0.0001182018,0.0002369947,0.0001016485,0.000504994,0.0001794949,0.00003536057,0.00008837806],"category_scores_gemma":[0.00003423822,0.0001022987,0.00002718657,0.0007088272,0.00002947808,0.0003735263,0.00007750575,0.0002862854,0.0001640933],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007325413,"about_ca_system_score_gemma":0.00009989792,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001592637,"about_ca_topic_score_gemma":0.0000148228,"domain_scores_codex":[0.9986829,0.000109324,0.0002166252,0.0003937437,0.000323737,0.0002737146],"domain_scores_gemma":[0.9995995,0.0001475627,0.00004379233,0.000105009,0.00003788784,0.00006625514],"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":[0.00006058052,0.0002399046,0.006152931,0.00016411,0.00007414143,0.0005008815,0.03858404,0.3113802,0.02055225,0.1512043,0.0002990176,0.4707876],"study_design_scores_gemma":[0.0004077449,0.0001878675,0.002203153,0.0001193536,0.000003996245,0.00002413288,0.0015717,0.992319,0.000665907,0.00004662231,0.002274559,0.0001759327],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2641151,0.00007195605,0.7263053,0.0003635287,0.0002187596,0.0001885185,9.12322e-8,0.0004776405,0.008259071],"genre_scores_gemma":[0.9697741,0.000002572213,0.02693609,0.0001080245,0.00006852088,0.00002159711,0.000004327494,0.00001321253,0.003071505],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.705659,"threshold_uncertainty_score":0.4869669,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009472611361995722,"score_gpt":0.2623042185625421,"score_spread":0.2528316072005464,"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."}}