{"type":"ScholarlyArticle","title":"PMCE: Probabilistic Multi-Granularity Semantics with Caption-Guided Enhancement for Few-Shot Learning","authors":[{"name":"Jiaying Wu","slug":"jiaying-wu","given":"Jiaying","family":"Wu","affiliation":""},{"name":"Can Gao","slug":"can-gao","given":"Can","family":"Gao","affiliation":""},{"name":"Jinglu Hu","slug":"jinglu-hu","given":"Jinglu","family":"Hu","affiliation":""},{"name":"Hui Li","slug":"hui-li","given":"Hui","family":"Li","affiliation":""},{"name":"Xiaofeng Cao","slug":"xiaofeng-cao","given":"Xiaofeng","family":"Cao","affiliation":""},{"name":"Jingcai Guo","slug":"jingcai-guo","given":"Jingcai","family":"Guo","affiliation":""}],"abstract":"Few-shot learning aims to recognize novel categories from limited labeled samples, where prototypes estimated from 1--5 supports per class are often unreliable. Semantic-based approaches alleviate this by introducing class-level priors, but they often ignore instance-level cues and rarely optimize queries under the inductive protocol. We propose PMCE, a Probabilistic framework that leverages Multi-granularity semantics with Caption-guided Enhancement for few-shot classification. On base classes, we build a knowledge bank with class-wise visual statistics and class-name embeddings. At test time, the semantic embedding of a novel class retrieves a few similar base classes whose visual priors are aggregated into a class-specific prior and combined with the support-based prototype via MAP estimation. Simultaneously, we train a lightweight enhancer on base classes that fuses frozen BLIP captions with visual features, and apply it to both supports and queries without using query-set statistics or novel labels. A simple caption-consistency regularizer further improves robustness to noisy captions. Experiments on four standard benchmarks with ResNet-12 and Swin-T backbones show that PMCE outperforms state-of-the-art few-shot baselines, achieving up to 7.71% gains over the strongest competitor on MiniImageNet in the challenging 1-shot setting. Our code is available at https://github.com/channa419/PMCE.","doi":"10.24963/ijcai.2026/206","url":"https://ijcai.org/proceedings/2026/206","pdf":"https://ijcai.org/proceedings/2026/0206.pdf","markdown":"https://ijcai.org/proceedings/2026/206.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/206","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Computer Vision","track":"Main Track","number":206,"pages":{"first":1848,"last":1856},"keywords":["Computer Vision: Transfer, low-shot, semi- and un- supervised learning","Machine Learning: Learning sparse models","Machine Learning: Open-World/Open-Set/OOD Learning","Machine Learning: Foundation models","Machine Learning: Cost-sensitive learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}