{"id":"W3127215335","doi":"10.1609/aaai.v35i9.16969","title":"Show, Attend and Distill: Knowledge Distillation via Attention-based Feature Matching","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":145,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Distillation; Computer science; Feature (linguistics); Matching (statistics); Artificial intelligence; Machine learning; Selection (genetic algorithm); Control (management); Knowledge transfer; Mathematics; Knowledge management; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008660458,0.001163105,0.0009957151,0.001376051,0.0007528852,0.001002372,0.002788475,0.001702291,0.004592468],"category_scores_gemma":[0.003565012,0.0005859807,0.0009447217,0.001213693,0.001062181,0.004673275,0.002774351,0.002074433,0.001401735],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007201168,"about_ca_system_score_gemma":0.001004544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00492294,"about_ca_topic_score_gemma":0.006928398,"domain_scores_codex":[0.9994633,0.0001183029,0.00002508439,0.0002073493,0.0001182612,0.00006765273],"domain_scores_gemma":[0.9991441,0.0003755638,0.00006320071,0.0002696593,0.00008819676,0.00005928641],"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":[0.0003952795,0.0003397641,0.001066219,0.000237819,0.0001308145,0.0002602775,0.00030254,0.121343,0.02620775,0.01906424,0.01191421,0.8187381],"study_design_scores_gemma":[0.00003393022,0.00008927716,0.0002836657,0.00001425104,0.00002813765,0.00009109097,0.00004466041,0.9521351,0.01642149,0.02712637,0.003706516,0.00002558212],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03549199,0.0005269392,0.9517459,0.0003611925,0.00009236396,0.0001238902,0.0003803289,0.008487231,0.002790229],"genre_scores_gemma":[0.4952637,0.00032904,0.4927371,0.0006515748,0.00008582773,0.0002247415,0.001754918,0.0008628013,0.008090291],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00492294,"threshold_uncertainty_score":0.0153634,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04860094291411718,"score_gpt":0.2885622224527176,"score_spread":0.2399612795386004,"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."}}