{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002034605,0.0015173,0.002036447,0.003229376,0.000628161,0.001294148,0.003770307,0.002609357,0.002239432],"category_scores_gemma":[0.005659422,0.000637326,0.002174183,0.003381621,0.0008614262,0.003434089,0.002545888,0.001667916,0.001500124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008637987,"about_ca_system_score_gemma":0.001066618,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004685661,"about_ca_topic_score_gemma":0.00470508,"domain_scores_codex":[0.9980499,0.0004578235,0.00008211612,0.0007196107,0.0004547388,0.0002359469],"domain_scores_gemma":[0.998367,0.0006200739,0.000176327,0.0004998075,0.0002773982,0.00005929122],"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":[0.0004462703,0.0001878814,0.001745913,0.0002166058,0.0002718566,0.0002635397,0.0002583659,0.09642939,0.02091056,0.01281441,0.01310142,0.8533538],"study_design_scores_gemma":[0.00004794316,0.00006319469,0.0006358664,0.00001680945,0.00004454034,0.0002825111,0.00005381247,0.9675989,0.007424156,0.0201771,0.003622343,0.00003284431],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007524186,0.0004724192,0.9885633,0.00008773891,0.00004187221,0.00005429866,0.0002291651,0.002592005,0.0004349416],"genre_scores_gemma":[0.3352773,0.0006785418,0.6555254,0.0004789291,0.0003220871,0.000267402,0.002947943,0.001131313,0.003371017],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004685661,"threshold_uncertainty_score":0.01076013,"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."}}