A2D2C: Adaptive attention-driven dynamic convolution for local feature adaptation

Pattern Recognition 2026 Open access

Read full text
Authors: Tianyu Zhang, Fan Wan, Xingyu Miao, Jingjing Deng, Xianghua Xie, Yang Long
DOI: 10.1016/j.patcog.2026.113915
Cited by: 1
References: 21

Abstract

• Introduces A 2 D 2 C: attention-driven dynamic convolution for local adaptation. • Uses multi-point random sampling to route and fuse k base kernels efficiently. • Presents A 2 D 2 C ＋ that fuses kernels once, cutting redundancy and MAdds at parity. • Shows consistent gains on ImageNet, CIFAR-100 and COCO with statistical reports.

Fields of Study & Subjects

Face recognition and analysis Domain Adaptation and Few-Shot Learning Advanced Neural Network Applications

Publication details

Journal / source
Pattern Recognition
Publisher
Elsevier BV
Volume
180
Pages
113915–113915
Publication date
26 May 2026
Language
EN