{"id":"W4404673562","doi":"10.1007/978-3-031-73024-5_4","title":"Modality Translation for Object Detection Adaptation Without Forgetting Prior Knowledge","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":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Forgetting; Modality (human–computer interaction); Adaptation (eye); Translation (biology); Artificial intelligence; Object (grammar); Computer vision; Natural language processing; Cognitive psychology; Neuroscience; 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":[0.001631974,0.0004542326,0.000410426,0.0008785833,0.000453665,0.0007865929,0.001101259,0.0003196904,0.000005296035],"category_scores_gemma":[0.0001344153,0.000445478,0.0002074262,0.0006753697,0.0002213974,0.0008751938,0.0002382703,0.0006907576,0.00003941479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003888425,"about_ca_system_score_gemma":0.0004895191,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001488078,"about_ca_topic_score_gemma":0.0002835023,"domain_scores_codex":[0.9967123,0.00004680438,0.0006089403,0.001465713,0.0006355651,0.0005306245],"domain_scores_gemma":[0.9979736,0.0006574293,0.0002908578,0.0006300406,0.0003199703,0.0001280731],"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":[0.00001223236,0.0000122262,0.000003854169,0.0001121898,0.0000109737,0.000003370787,0.003838798,0.04407637,0.0004266342,0.01458278,0.000001226965,0.9369193],"study_design_scores_gemma":[0.0003006658,0.0001321873,0.00003439171,0.0002888887,0.00001603409,0.00001726762,0.000001517238,0.8446373,0.001147545,0.1500571,0.002939219,0.0004279329],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00006719136,0.0007254518,0.9910777,0.0004901155,0.002476342,0.0009185254,0.000004694721,0.0004034216,0.003836535],"genre_scores_gemma":[0.5136555,0.00001504539,0.4846611,0.0002210845,0.0005281118,0.0000457269,0.00001064985,0.00005142096,0.0008112709],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9364914,"threshold_uncertainty_score":0.9997997,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03939968520406524,"score_gpt":0.289039440942685,"score_spread":0.2496397557386198,"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."}}