{"id":"W4413156549","doi":"10.1109/cvpr52734.2025.00432","title":"DSV-LFS: Unifying LLM-Driven Semantic Cues with Visual Features for Robust Few-Shot Segmentation","year":2025,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Shot (pellet); Segmentation; Artificial intelligence; Image segmentation; Computer vision; Natural language processing","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001464355,0.002318006,0.002220893,0.002886806,0.0007231871,0.002003475,0.004456274,0.002273572,0.005119407],"category_scores_gemma":[0.003990944,0.0008940409,0.002123067,0.0017629,0.001331671,0.003964013,0.003991832,0.002276136,0.002704546],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001763866,"about_ca_system_score_gemma":0.002070504,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009481785,"about_ca_topic_score_gemma":0.01508079,"domain_scores_codex":[0.998657,0.0002068111,0.00007679447,0.0005298242,0.000358211,0.0001713689],"domain_scores_gemma":[0.9987748,0.000384664,0.0001098961,0.0003385588,0.000268718,0.000123368],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008087911,0.0003318598,0.00119822,0.0006010879,0.0002098588,0.0003074248,0.0004365319,0.09052221,0.06979772,0.01255081,0.01964345,0.803592],"study_design_scores_gemma":[0.00004094292,0.0001162414,0.0003546929,0.00003405435,0.00003662743,0.0001134672,0.00009991362,0.9576171,0.01784731,0.01757564,0.006121578,0.00004245705],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01238637,0.0006701423,0.9707774,0.0001880923,0.0001066558,0.0001916613,0.0008763369,0.01341219,0.001391056],"genre_scores_gemma":[0.2165854,0.0004789289,0.7676689,0.000771476,0.0001520397,0.0004385535,0.007023213,0.002371272,0.004510233],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009481785,"threshold_uncertainty_score":0.01885319,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02812949130331487,"score_gpt":0.3043512071728003,"score_spread":0.2762217158694854,"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."}}