{"id":"W2145276819","doi":"","title":"Transfer Learning by Borrowing Examples for Multiclass Object Detection","year":2011,"lang":"en","type":"article","venue":"DSpace@MIT (Massachusetts Institute of Technology)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":114,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Science Foundation","keywords":"Object (grammar); Computer science; Object detection; Class (philosophy); Artificial intelligence; Transfer of learning; Detector; Machine learning; Training set; Transfer (computing); Pattern recognition (psychology)","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":[0.0001880503,0.0002928124,0.0003507345,0.0004286088,0.0003837611,0.00002908786,0.001191402,0.0003373061,0.000002932767],"category_scores_gemma":[0.0001820842,0.0003020659,0.0001450385,0.00116239,0.0003339106,0.001067774,0.0001862642,0.0004518143,0.000008883485],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008694156,"about_ca_system_score_gemma":0.00004631056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003144917,"about_ca_topic_score_gemma":0.00008559976,"domain_scores_codex":[0.9980964,0.00002841229,0.0004218323,0.0007072311,0.000208838,0.0005372747],"domain_scores_gemma":[0.9987063,0.00007702641,0.0001643722,0.0008161663,0.0001516334,0.000084537],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005526164,0.0002724131,0.001659112,0.00008185526,0.0001564937,0.00001052173,0.0008172637,0.001723308,0.5593817,0.08091129,0.0005457299,0.3543851],"study_design_scores_gemma":[0.001018805,0.0003687979,0.0002653574,0.00005620588,0.00004820642,0.00002515614,0.0001045457,0.01617944,0.7500273,0.005657335,0.2257199,0.0005289497],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09940033,0.0002932507,0.8966203,0.001137593,0.0003323648,0.0006701501,0.00001659122,0.001165927,0.0003634928],"genre_scores_gemma":[0.8033844,0.00005239229,0.1960231,0.00006622408,0.00002653164,0.0002870417,0.000006939233,0.00002868149,0.0001246996],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7039841,"threshold_uncertainty_score":0.9999431,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02650799746629797,"score_gpt":0.2465805068313671,"score_spread":0.2200725093650691,"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."}}