{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004592135,0.001080532,0.0008073244,0.0004672474,0.0003809575,0.001721585,0.001908407,0.001104668,0.01652284],"category_scores_gemma":[0.001516455,0.000766467,0.0008676713,0.0003825139,0.0008282429,0.003771882,0.001849978,0.001261433,0.00734472],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006386099,"about_ca_system_score_gemma":0.0008515327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003102745,"about_ca_topic_score_gemma":0.007578095,"domain_scores_codex":[0.9996598,0.00003420694,0.00001327583,0.0001696332,0.00007269897,0.00005050798],"domain_scores_gemma":[0.9996064,0.00008939927,0.00003446794,0.0001747314,0.00005802777,0.00003699129],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000507456,0.0001584482,0.001531331,0.0003277732,0.00009012801,0.0001329033,0.0001592739,0.02962177,0.05442448,0.0241333,0.07893153,0.8099816],"study_design_scores_gemma":[0.00007975136,0.0001407978,0.001162618,0.00007075396,0.00005086956,0.0002544638,0.0001373472,0.8250989,0.07843336,0.06027701,0.03423648,0.00005767092],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0157339,0.0004421264,0.9287764,0.000513481,0.0001801247,0.00008818712,0.0009357629,0.0448298,0.008500267],"genre_scores_gemma":[0.2718844,0.0004127036,0.6995935,0.0005903683,0.0001188549,0.0001717975,0.003169689,0.004211731,0.01984688],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01652284,"threshold_uncertainty_score":0.05527437,"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."}}