{"id":"W3210701102","doi":"10.1007/978-3-030-88004-0_8","title":"Attentive Contrast Learning Network for Fine-Grained Classification","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Discriminative model; Artificial intelligence; Pairwise comparison; Contrast (vision); Feature learning; Leverage (statistics); Feature (linguistics); Representation (politics); Pattern recognition (psychology); Benchmark (surveying); Generator (circuit theory); Machine learning; Power (physics)","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":[0.001271913,0.0004502046,0.0005272316,0.0003918343,0.0005813309,0.0008309341,0.001678651,0.0002920814,0.00003280364],"category_scores_gemma":[0.0003867677,0.0004540839,0.0002054413,0.0006879538,0.000379336,0.0004589254,0.0005246262,0.0009063698,0.00003008486],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002365614,"about_ca_system_score_gemma":0.0005478327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004705026,"about_ca_topic_score_gemma":0.00005229492,"domain_scores_codex":[0.9963456,0.00008385849,0.0005571534,0.001550178,0.0007221547,0.0007410158],"domain_scores_gemma":[0.9968706,0.001175059,0.0004666063,0.0007685898,0.0005504406,0.0001686915],"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":[0.00001260429,0.00002035206,0.000117885,0.00003408855,0.00002469189,0.00003175743,0.0008698822,0.1551988,0.000320869,0.1429417,0.0001083799,0.7003189],"study_design_scores_gemma":[0.0005063041,0.0001496168,0.0005414034,0.0003291703,0.00001161181,0.00002526101,0.000001489111,0.9386202,0.0001079164,0.03697759,0.02213714,0.0005922685],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002579056,0.0004388248,0.9919968,0.001407253,0.001775651,0.0005212273,0.000003181312,0.0002015765,0.00362975],"genre_scores_gemma":[0.1203195,0.00004803979,0.8710924,0.001993617,0.001380272,0.00005417121,0.00008306147,0.00006840879,0.004960494],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7834214,"threshold_uncertainty_score":0.9997911,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02999113960115037,"score_gpt":0.2600533393372363,"score_spread":0.230062199736086,"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."}}