{"id":"W3194282644","doi":"10.1186/s10033-021-00598-9","title":"ML-ANet: A Transfer Learning Approach Using Adaptation Network for Multi-label Image Classification in Autonomous Driving","year":2021,"lang":"en","type":"article","venue":"Chinese Journal of Mechanical Engineering","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Shenzhen Fundamental Research and Discipline Layout project; National Natural Science Foundation of China","keywords":"Reproducing kernel Hilbert space; Artificial intelligence; Computer science; Pattern recognition (psychology); Transfer of learning; Kernel (algebra); Embedding; Image (mathematics); Domain adaptation; Feature (linguistics); Adaptation (eye); Matching (statistics); Mathematics; Hilbert space; Statistics","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":[0.0008213824,0.0001629168,0.000301385,0.0001938143,0.00007364069,0.0001399399,0.0004100465,0.0001227111,0.000002170147],"category_scores_gemma":[0.0006802034,0.0001428912,0.0001139283,0.0006505845,0.000009771564,0.0006837826,0.00006253903,0.0004297253,6.268866e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001333867,"about_ca_system_score_gemma":0.00009779524,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001420699,"about_ca_topic_score_gemma":0.000002541036,"domain_scores_codex":[0.9986568,0.00005708219,0.0005886953,0.0002380976,0.0002036824,0.000255624],"domain_scores_gemma":[0.9992186,0.0001838866,0.000158716,0.0001935252,0.0001770292,0.00006827673],"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":[0.00001363302,0.000193952,0.0002277168,0.00007284222,0.00004148192,0.00001974484,0.000494451,0.6813008,0.2494347,0.03212643,0.000006641615,0.03606763],"study_design_scores_gemma":[0.0008378755,0.00004674399,0.0009509714,0.00007317433,0.00001119606,0.00006526412,0.0001050734,0.9950806,0.001909843,0.0007086266,0.00006249658,0.0001480692],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08756585,0.0002688186,0.9114491,0.0002137872,0.0002697309,0.0001155729,3.524793e-7,0.0001095683,0.000007271689],"genre_scores_gemma":[0.5091503,0.00002160036,0.4907269,0.000008173273,0.00006471974,0.000006997091,0.000001866288,0.00001143286,0.000008017878],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4215844,"threshold_uncertainty_score":0.5826935,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04901093335217047,"score_gpt":0.2809918205667821,"score_spread":0.2319808872146116,"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."}}