{"id":"W4386978004","doi":"10.48550/arxiv.2309.12314","title":"TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Stephen's University","funders":"National Natural Science Foundation of China","keywords":"Distillation; Computer science; Inheritance (genetic algorithm); Modal; Artificial intelligence; Feature (linguistics); AKA; Machine learning; Transferability; Code (set theory); Scratch; Image (mathematics); Pattern recognition (psychology); Programming language; Chemistry; Chromatography","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":[0.0007016573,0.001814114,0.0008311578,0.0005008419,0.0006330602,0.001161952,0.003194442,0.001182734,0.01077471],"category_scores_gemma":[0.003554785,0.0006760397,0.0009270462,0.0006088504,0.0008506147,0.002717508,0.003203025,0.002883631,0.003502164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007537104,"about_ca_system_score_gemma":0.001404633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006938132,"about_ca_topic_score_gemma":0.01259573,"domain_scores_codex":[0.999499,0.00007548614,0.00002119023,0.0001633089,0.0001503671,0.00009066358],"domain_scores_gemma":[0.9994636,0.0001726847,0.00003448563,0.0001707722,0.0001073739,0.0000511553],"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":[0.0007432135,0.0002615246,0.001627182,0.0004147274,0.0001977613,0.0004276303,0.0002929165,0.1876073,0.05258851,0.01711513,0.0338735,0.7048507],"study_design_scores_gemma":[0.00004989596,0.00009950507,0.0002261726,0.000021502,0.0000244446,0.0001129585,0.00004421823,0.9579373,0.02590538,0.00727205,0.008267737,0.00003873761],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02913249,0.0005925686,0.9289023,0.0004315691,0.0003324882,0.0001850731,0.0009078726,0.03395502,0.005560556],"genre_scores_gemma":[0.3943815,0.0003774425,0.5771242,0.001460808,0.0002071105,0.000592218,0.004911655,0.004252139,0.01669281],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01077471,"threshold_uncertainty_score":0.03604496,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08317322424467298,"score_gpt":0.2121273096551278,"score_spread":0.1289540854104548,"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."}}