计算机科学
帕斯卡(单位)
目标检测
人工智能
分类器(UML)
判别式
特征提取
模式识别(心理学)
单发
学习迁移
边距(机器学习)
卷积神经网络
视觉对象识别的认知神经科学
一般化
机器学习
数学
程序设计语言
数学分析
物理
光学
作者
Shilong Hao,Wei Liu,Jie Yang
标识
DOI:10.1145/3625403.3625408
摘要
Few-shot object detection, which aims to improve the generalization ability of the object detection model with limited data, has gained significant attention. Many existing methods use standard Faster R-CNN as the basic model and add modules to assist the detector to adapt to novel classes. However, Faster R-CNN as a method designed for the traditional object detection task, does not consider the few-shot condition and lacks relevant design for the few-shot detection. In this paper, we present an effective transfer learning-based approach for few-shot object detection. We propose modifications to the Faster R-CNN structure to address specific challenges in few-shot scenarios. Our method introduces a decoupled feature extraction network to obtain clearer and more generalized features, mitigating conflicts between classification and regression. Additionally, a feature complementing branch is introduced to obtain discriminative features for novel classes during fine-tuning. Furthermore, we design a margin cosine loss to enhance the classifier’s performance. Compared with baseline, our method achieves an average improvement of +7.0 nAP50 on PASCAL VOC and +3.0 nAP on COCO. Experimental results show that our method can outperform many existing algorithms with the state-of-the-art performance achieved.
科研通智能强力驱动
Strongly Powered by AbleSci AI