{"id":"W6979284107","doi":"","title":"LookWhere? Efficient Visual Recognition by Learning Where to Look and What to See from Self-Supervision","year":2025,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada; Canadian Institute for Advanced Research","keywords":"Security token; Computation; Task (project management); Pruning; Code (set theory); Feature extraction; Matching (statistics); Quadratic growth; Visualization","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008061789,0.0001502682,0.0001384075,0.0001397096,0.000267018,0.0001952588,0.0004372776,0.00006614999,0.00002271202],"category_scores_gemma":[0.00001494222,0.0001772057,0.0000352648,0.001001294,0.00002309373,0.0006726256,0.0005436362,0.0001626182,0.0003260349],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001099236,"about_ca_system_score_gemma":0.0000253416,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004939397,"about_ca_topic_score_gemma":0.00003730625,"domain_scores_codex":[0.9987192,0.00007694742,0.0001188727,0.0007734523,0.00006682516,0.0002447514],"domain_scores_gemma":[0.9991692,0.0001709464,0.00004472955,0.0003387154,0.00008762257,0.000188841],"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":[0.0001895193,0.0006313801,0.005304151,0.00005307321,0.0001275076,0.0001034762,0.002385153,0.521866,0.02397028,0.02256977,0.009255437,0.4135442],"study_design_scores_gemma":[0.0009392748,0.0002544377,0.001842221,0.0002792123,0.00005200467,0.000002324669,0.0009645083,0.9556434,0.003305766,0.006718603,0.02936129,0.000636966],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5025358,0.0001329885,0.4963166,0.0003856387,0.00007652983,0.0002014892,0.000002477363,0.0001615264,0.0001869493],"genre_scores_gemma":[0.990479,0.0003490559,0.007619944,0.0006446328,0.00002416856,0.000002547592,0.00001169767,0.000009788562,0.0008591932],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4886967,"threshold_uncertainty_score":0.7226238,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02054199652657172,"score_gpt":0.1963128637669944,"score_spread":0.1757708672404227,"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."}}