Pattern Analysis and Applications Computer Vision and Pattern Recognition

CCD-GFSOD: centroid calibration and dynamic constraint for generalized few-shot object detection

Liu, Zhoufeng, Huangfu, Yi, Ding, Shumin, Wang, Junpu, Li, Chunlei, Ma, Yongli
Springer Nature · 2026-10-15 · DOI 10.1007/s10044-026-01790-0

Abstract

Generalized few-shot object detection (GFSOD) aims to detect base and novel classes simultaneously under limited annotations, playing an important role in real-world applications like autonomous driving and intelligent surveillance with emerging novel objects. Nevertheless, existing detectors suffer from two difficulties: unstable novel-class features without stable global semantic references, and semantic confusion between visually similar base-novel pairs that blurs decision boundaries. This paper presents CCD-GFSOD, a two-stage framework consisting of the Centroid-based Feature Calibration Module (CFCM) and Dynamic Discriminative Constraint Module (DDCM). CFCM constructs learnable global semantic centroids from base-class data using cross-batch exponential moving average to calibrate novel-class features and suppress intra-class dispersion during finetuning. DDCM imposes adaptive logit margin constraints on the most confusing categories identified by feature-prototype similarity, so as to sharpen inter-class boundaries. Experiments on PASCAL VOC and MS COCO show 54.1% nAP50 and 72.1% AP50 on VOC, and 18.4% nAP and 31.8% AP on COCO, outperforming baselines. The method improves detection stability with negligible extra computation. Our code is available at https://github.com/hfy650/CCD-GFSOD .

Read at publisher →