{"id":"W4287756009","doi":"10.48550/arxiv.2006.12245","title":"Enhancing Few-Shot Image Classification with Unlabelled Examples","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency; Canada Research Chairs; Compute Canada","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Machine learning; Mahalanobis distance; Code (set theory); Feature (linguistics); Cluster analysis; Shot (pellet); Image (mathematics); Set (abstract data type); Contextual image classification; Test set; Training set; Data mining","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002805232,0.0003648303,0.0003675433,0.0002386693,0.0002786801,0.0003367629,0.001557378,0.0002058839,0.00007707384],"category_scores_gemma":[0.00007464796,0.0003936575,0.0001374601,0.0008393285,0.0001306667,0.000565901,0.00102625,0.0007618311,0.0002882802],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001946429,"about_ca_system_score_gemma":0.0003432661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000743956,"about_ca_topic_score_gemma":0.00006383762,"domain_scores_codex":[0.9975612,0.0002347405,0.0002606458,0.001391688,0.0001781214,0.0003735944],"domain_scores_gemma":[0.9978729,0.00017346,0.0004186973,0.001049575,0.0002241611,0.0002611707],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000251435,0.0002551054,0.002687089,0.0003932165,0.0003931258,0.001105309,0.005273035,0.08882281,0.02121934,0.875504,0.0007724746,0.003323022],"study_design_scores_gemma":[0.001442888,0.0001645801,0.006326742,0.0002391674,0.000122133,0.00001174214,0.001241071,0.9671187,0.001859922,0.01515435,0.005137724,0.001180936],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05197308,0.00003010107,0.9362907,0.000516967,0.0002402899,0.0003194659,0.000004874916,0.0005328117,0.01009173],"genre_scores_gemma":[0.9684235,0.00007532581,0.02968549,0.0002481943,0.00007470274,0.000002201845,0.00003867152,0.00003034774,0.00142155],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9164504,"threshold_uncertainty_score":0.9998515,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1442749862236249,"score_gpt":0.2092672225856921,"score_spread":0.06499223636206722,"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."}}