Skip to main content
placeholder image

Kernelized Few-shot Object Detection with Efficient Integral Aggregation

Conference Paper


Abstract


  • We design a Kernelized Few-shot Object Detector by leveraging kernelized matrices computed over multiple proposal regions, which yield expressive non-linear representations whose model complexity is learned on the fly. Our pipeline contains several modules. An Encoding Network encodes support and query images. Our Kernelized Autocorrelation unit forms the linear, polynomial and RBF kernelized representations from features extracted within support regions of support images. These features are then cross-correlated against features of a query image to obtain attention weights, and generate query proposal regions via an Attention Region Proposal Net. As the query proposal regions are many, each described by the linear, polynomial and RBF kernelized matrices, their formation is costly but that cost is reduced by our proposed Integral Region-of-Interest Aggregation unit. Finally, the Multi-head Relation Net combines all kernelized (second-order) representations with the first-order feature maps to learn support-query class relations and locations. We outperform the state of the art on novel classes by 3.8%, 5.4% and 5.7% mAP on PASCAL VOC 2007, FSOD, and COCO.

Publication Date


  • 2022

Citation


  • Zhang, S., Wang, L., Murray, N., & Koniusz, P. (2022). Kernelized Few-shot Object Detection with Efficient Integral Aggregation. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Vol. 2022-June (pp. 19185-19194). doi:10.1109/CVPR52688.2022.01861

Scopus Eid


  • 2-s2.0-85140198588

Web Of Science Accession Number


Start Page


  • 19185

End Page


  • 19194

Volume


  • 2022-June

Issue


Place Of Publication


Abstract


  • We design a Kernelized Few-shot Object Detector by leveraging kernelized matrices computed over multiple proposal regions, which yield expressive non-linear representations whose model complexity is learned on the fly. Our pipeline contains several modules. An Encoding Network encodes support and query images. Our Kernelized Autocorrelation unit forms the linear, polynomial and RBF kernelized representations from features extracted within support regions of support images. These features are then cross-correlated against features of a query image to obtain attention weights, and generate query proposal regions via an Attention Region Proposal Net. As the query proposal regions are many, each described by the linear, polynomial and RBF kernelized matrices, their formation is costly but that cost is reduced by our proposed Integral Region-of-Interest Aggregation unit. Finally, the Multi-head Relation Net combines all kernelized (second-order) representations with the first-order feature maps to learn support-query class relations and locations. We outperform the state of the art on novel classes by 3.8%, 5.4% and 5.7% mAP on PASCAL VOC 2007, FSOD, and COCO.

Publication Date


  • 2022

Citation


  • Zhang, S., Wang, L., Murray, N., & Koniusz, P. (2022). Kernelized Few-shot Object Detection with Efficient Integral Aggregation. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Vol. 2022-June (pp. 19185-19194). doi:10.1109/CVPR52688.2022.01861

Scopus Eid


  • 2-s2.0-85140198588

Web Of Science Accession Number


Start Page


  • 19185

End Page


  • 19194

Volume


  • 2022-June

Issue


Place Of Publication