{"id":"W2613498939","doi":"10.1109/tpami.2018.2884462","title":"Incremental Learning Through Deep Adaptation","year":2018,"lang":"en","type":"preprint","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Air Force Office of Scientific Research; Canada Research Chairs","keywords":"Computer science; Artificial intelligence; Adaptation (eye); Quantization (signal processing); Task (project management); Network architecture; Artificial neural network; Machine learning; Domain adaptation; Range (aeronautics); Domain (mathematical analysis); Network performance; Deep neural networks; Algorithm; Classifier (UML); Mathematics; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008441987,0.0009522866,0.000916808,0.0006323113,0.000310699,0.0007003923,0.002150638,0.0008301866,0.002527551],"category_scores_gemma":[0.00378662,0.0005219859,0.0006066232,0.0005924696,0.0007293431,0.001959358,0.00178069,0.001758501,0.0008768777],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006155912,"about_ca_system_score_gemma":0.000736095,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002460005,"about_ca_topic_score_gemma":0.004193884,"domain_scores_codex":[0.999629,0.00006950107,0.00001825365,0.0001308075,0.0001025461,0.0000497613],"domain_scores_gemma":[0.9991221,0.0003587024,0.00006051895,0.0002428965,0.0001623335,0.00005345568],"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":[0.000168889,0.0002175443,0.001886019,0.0001678169,0.0001353042,0.0001271397,0.00013669,0.4832286,0.01677005,0.01556807,0.00741952,0.4741744],"study_design_scores_gemma":[0.00001066972,0.00002948069,0.0001721746,0.000008586122,0.00001250861,0.00003001516,0.000009697984,0.9885551,0.002384971,0.007750175,0.001028956,0.00000750457],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0255404,0.0004539732,0.9680723,0.0001636209,0.00008378772,0.0000740821,0.00007985418,0.002456875,0.003075066],"genre_scores_gemma":[0.6501115,0.0005027723,0.34128,0.0004924638,0.0001239666,0.0002978876,0.0005318781,0.0003347995,0.006324669],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002527551,"threshold_uncertainty_score":0.008455575,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03901779770268217,"score_gpt":0.2917025047683656,"score_spread":0.2526847070656834,"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."}}