{"id":"W2903585023","doi":"10.1609/aaai.v33i01.33013412","title":"Spatially Invariant Unsupervised Object Detection with Convolutional Neural Networks","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":112,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Samsung","keywords":"Computer science; Artificial intelligence; Interpretability; Object detection; Object (grammar); Convolutional neural network; Cognitive neuroscience of visual object recognition; Generalization; Transfer of learning; Machine learning; Invariant (physics); Unsupervised learning; Pattern recognition (psychology)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006248084,0.0009654729,0.0005953092,0.0007447462,0.0003040652,0.0007448256,0.001941237,0.0008423168,0.0008968958],"category_scores_gemma":[0.001895924,0.0005716744,0.0007120249,0.0007973413,0.0007596941,0.001586862,0.001185512,0.001344694,0.0004647579],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00111382,"about_ca_system_score_gemma":0.0008169701,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01037505,"about_ca_topic_score_gemma":0.01560079,"domain_scores_codex":[0.9995957,0.00005465403,0.0000170031,0.0001651157,0.0001052748,0.00006228771],"domain_scores_gemma":[0.9992437,0.0002615144,0.0001448043,0.0001834173,0.0001285722,0.00003803226],"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":[0.0002144077,0.0001764012,0.00287411,0.0001302552,0.0001995733,0.0002025062,0.0001610127,0.5430193,0.05878775,0.0210112,0.004216777,0.3690068],"study_design_scores_gemma":[0.00000363405,0.00001808237,0.0004093656,0.000004442124,0.000008900364,0.000024286,0.000005715441,0.9883958,0.00544988,0.005132453,0.0005405816,0.000006885687],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04896459,0.0004686975,0.9452502,0.0002051521,0.00003862546,0.0000382798,0.0001615739,0.002716545,0.002156212],"genre_scores_gemma":[0.6285602,0.0004784931,0.3632758,0.0002797259,0.00007043213,0.00009776528,0.0008968721,0.0002216382,0.006118946],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01037505,"threshold_uncertainty_score":0.02062935,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03753807711940282,"score_gpt":0.2539223336304387,"score_spread":0.2163842565110359,"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."}}