{"id":"W4382458246","doi":"10.1609/aaai.v37i2.25341","title":"TopicFM: Robust and Interpretable Topic-Assisted Feature Matching","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"National Research Foundation of Korea; Ministry of Trade, Industry and Energy; National Research Foundation","keywords":"Interpretability; Computer science; Discriminative model; Artificial intelligence; ENCODE; Robustness (evolution); Pattern recognition (psychology); Probabilistic logic; Matching (statistics); Feature extraction; Machine learning; Mathematics","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":[0.0003146167,0.000176534,0.0002185052,0.0001301077,0.0001880239,0.0002848309,0.001213708,0.00008770068,0.00001524715],"category_scores_gemma":[0.0002591414,0.0001292754,0.00007318525,0.0008342334,0.0001398046,0.000591142,0.0006431008,0.000300886,0.00002742909],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002664261,"about_ca_system_score_gemma":0.00003381608,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001928259,"about_ca_topic_score_gemma":0.000004393228,"domain_scores_codex":[0.9987005,0.00001211759,0.000287509,0.0004147157,0.0002909212,0.0002942252],"domain_scores_gemma":[0.9991269,0.00008459631,0.0001831361,0.0002619148,0.0002772874,0.00006617074],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002155816,0.00003175785,0.0001470668,0.0000561891,0.000009912585,0.000001678089,0.001124716,0.00001200152,0.0483432,0.6704894,0.0005283584,0.2792341],"study_design_scores_gemma":[0.00002057313,0.0001303409,0.0009128887,0.0003009976,0.000007319626,0.00001023651,0.0004565955,0.0133175,0.6128743,0.3711703,0.0005887555,0.0002102414],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1783317,0.0001393894,0.7709972,0.01966497,0.0009566931,0.001006812,0.000008332129,0.001261374,0.02763351],"genre_scores_gemma":[0.9826123,0.0001477526,0.01529065,0.0002718378,0.00004853979,0.00001824085,4.042269e-7,0.00001014407,0.001600185],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8042806,"threshold_uncertainty_score":0.5271698,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07783017532151877,"score_gpt":0.313445366723528,"score_spread":0.2356151914020092,"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."}}