In:
ACM Transactions on Multimedia Computing, Communications, and Applications, Association for Computing Machinery (ACM)
Abstract:
Classifying and accurately locating a visual category with few annotated training samples in computer vision has motivated the few-shot object detection technique, which exploits to transfer the source-domain detection model to the target domain. Under this paradigm, however, such transferred source-domain detection model usually encounters difficulty in the classification of target-domain because of the low data diversity of novel training samples. To combat this, we present a simple yet effective few-shot detector, Transferable RCNN. To transfer general knowledge learned from data-abundant base classes to data-scarce novel classes, we propose a weight transfer strategy to promote model transferability and an attention-based feature enhancement mechanism to learn more robust object proposal feature representations. Further, we ensure strong discrimination by optimizing the contrastive objectives of feature maps via a supervised spatial contrastive loss. Meanwhile, we introduce an angle-guided additive margin classifier to augment instances-level inter-class difference and intra-class compactness, which is beneficial for improving the discriminative power of the few-shot classification head under a few supervisions. Our proposed framework outperforms the current works in various settings of PASCAL VOC and MSCOCO datasets, this demonstrates the effectiveness and generalization ability.
Type of Medium:
Online Resource
ISSN:
1551-6857
,
1551-6865
Language:
English
Publisher:
Association for Computing Machinery (ACM)
Publication Date:
2023
detail.hit.zdb_id:
2182650-X
Bookmarklink
