{"id":"W2074652467","doi":"10.1109/tmm.2012.2234729","title":"An Unsupervised Hierarchical Feature Learning Framework for One-Shot Image Recognition","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Multimedia","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Artificial intelligence; Pyramid (geometry); Pattern recognition (psychology); Cognitive neuroscience of visual object recognition; Feature (linguistics); Feature extraction; Domain (mathematical analysis); Machine learning; Feature learning; Domain knowledge; Matching (statistics)","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":[0.0002597546,0.0002298151,0.0002144542,0.0002427003,0.0004911265,0.0003824884,0.0004684512,0.0002543328,0.0004808537],"category_scores_gemma":[0.00007831112,0.000236356,0.0001563316,0.0003986167,0.00008320543,0.00112424,0.000002237271,0.001022681,0.0006260769],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005122745,"about_ca_system_score_gemma":0.00005629447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000244189,"about_ca_topic_score_gemma":0.000007457073,"domain_scores_codex":[0.9981961,0.0002171667,0.0002495694,0.0005674861,0.0003388029,0.0004308943],"domain_scores_gemma":[0.9982185,0.000747558,0.00008364128,0.0004183961,0.0002130372,0.0003189022],"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":[0.00007403559,0.0004897717,0.00001434754,0.00002859782,0.00004891131,0.000003807182,0.00393241,0.005026273,0.03185002,0.000336213,0.000195413,0.9580002],"study_design_scores_gemma":[0.001523403,0.0006157619,0.001272354,0.00009537835,0.00003133818,0.000009197967,0.0004340169,0.9705554,0.0178735,0.005544315,0.001482495,0.0005629002],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01161352,0.00001035093,0.9845975,0.001693145,0.0006329177,0.0006311871,0.00001376663,0.0005387337,0.0002688963],"genre_scores_gemma":[0.4127859,0.0000158899,0.5859828,0.0005256754,0.0001154587,0.0002333535,0.00002607947,0.00002905182,0.0002857368],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9655291,"threshold_uncertainty_score":0.9638317,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05355395215045962,"score_gpt":0.3000440028239455,"score_spread":0.2464900506734859,"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."}}