{"id":"W4287706274","doi":"10.48550/arxiv.2007.12562","title":"Hallucinating Saliency Maps for Fine-Grained Image Classification for\\n Limited Data Domains","year":2020,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Hallucinating; Artificial intelligence; Computer science; Benchmark (surveying); Image (mathematics); Task (project management); Pipeline (software); Pattern recognition (psychology); RGB color model; Object (grammar); Contextual image classification; Saliency map; Training set; Computer vision; Machine learning","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.001320322,0.0007827316,0.0007705732,0.0005502318,0.001207788,0.0006321113,0.005197175,0.0005800326,0.00003808855],"category_scores_gemma":[0.001025432,0.0009847078,0.0006446763,0.001901617,0.0002709836,0.001919787,0.003290413,0.0007218053,0.0001113464],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004262801,"about_ca_system_score_gemma":0.00046024,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006919982,"about_ca_topic_score_gemma":0.0001242013,"domain_scores_codex":[0.9932911,0.0003837053,0.0009555243,0.004188793,0.0002734638,0.0009073822],"domain_scores_gemma":[0.9932652,0.000578812,0.001304582,0.003345965,0.001036282,0.000469135],"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":[0.001174621,0.001414012,0.0007790785,0.002272407,0.0006752532,0.0001205126,0.002010385,0.01244271,0.02110166,0.9198184,0.008300361,0.02989059],"study_design_scores_gemma":[0.00261748,0.0005524118,0.001404735,0.0001691016,0.0003336765,0.000006555728,0.000502936,0.9374171,0.000362741,0.04955761,0.006083846,0.0009917598],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01864239,0.0000287447,0.9719061,0.002349051,0.001992893,0.002764641,0.0008210275,0.0004892892,0.001005821],"genre_scores_gemma":[0.9661645,0.0001324049,0.02915756,0.0002561892,0.000418137,0.0000241833,0.001922374,0.00007369159,0.001850901],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9475222,"threshold_uncertainty_score":0.9992603,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2707938877245558,"score_gpt":0.2705015552424624,"score_spread":0.0002923324820933715,"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."}}