{"type":"ScholarlyArticle","title":"A₃B₂: Adaptive Asymmetric Adapter for Alleviating Branch Bias in Vision-Language Image Classification with Few-Shot Learning","authors":[{"name":"Yiyun Zhou","slug":"yiyun-zhou","given":"Yiyun","family":"Zhou","affiliation":""},{"name":"Zhonghua Jiang","slug":"zhonghua-jiang","given":"Zhonghua","family":"Jiang","affiliation":""},{"name":"Wenkang Han","slug":"wenkang-han","given":"Wenkang","family":"Han","affiliation":""},{"name":"Kunxi Li","slug":"kunxi-li","given":"Kunxi","family":"Li","affiliation":""},{"name":"Mingjing Xu","slug":"mingjing-xu","given":"Mingjing","family":"Xu","affiliation":""},{"name":"Chang Yao","slug":"chang-yao","given":"Chang","family":"Yao","affiliation":""},{"name":"Jingyuan Chen","slug":"jingyuan-chen","given":"Jingyuan","family":"Chen","affiliation":""}],"abstract":"Efficient transfer learning methods for large-scale vision–language models (e.g., CLIP) enable strong few-shot transfer, yet existing adaptation methods follow a fixed fine-tuning paradigm that implicitly assumes a uniform importance of the image and text branches, which has not been systematically studied in image classification. Through extensive analysis, we reveal a Branch Bias issue in vision–language image classification: adapting the image encoder does not always improve performance under out-of-distribution settings. Motivated by this observation, we propose A₃B₂, an Adaptive Asymmetric Adapter that alleviates Branch Bias in few-shot learning. A₃B₂ introduces Uncertainty-Aware Adapter Dampening (UAAD), which automatically suppresses image-branch adaptation when prediction uncertainty is high, enabling soft and data-driven control without manual intervention. Architecturally, A₃B₂ adopts a lightweight asymmetric design inspired by mixture-of-experts with Load Balancing Regularization. Extensive experiments demonstrate that A₃B₂ consistently outperforms 11 competitive prompt- and adapter-based baselines.","doi":"10.24963/ijcai.2026/238","url":"https://ijcai.org/proceedings/2026/238","pdf":"https://ijcai.org/proceedings/2026/0238.pdf","markdown":"https://ijcai.org/proceedings/2026/238.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/238","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":238,"pages":{"first":2136,"last":2144},"keywords":["Computer Vision: Transfer, low-shot, semi- and un- supervised learning","Computer Vision: Multimodal learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}