QQ客服 官方微博 反馈留言

	LSTD: A Low-Shot Transfer Detector for Object Detection
	Hao Chen; Yali Wang; Guoyou Wang; Yu Qiao
	2018
会议日期	2018
会议地点	美国
英文摘要	Recent advances in object detection are mainly driven by deep learning with large-scale detection benchmarks. However, the fully-annotated training set is often limited for a target detection task, which may deteriorate the performance of deep detectors. To address this challenge, we propose a novel low-shot transfer detector (LSTD) in this paper, where we leverage rich source-domain knowledge to construct an effective target-domain detector with very few training examples. The main contributions are described as follows. First, we design a flexible deep architecture of LSTD to alleviate transfer difficulties in low-shot detection. This architecture can integrate the advantages of both SSD and Faster RCNN in a unified deep framework. Second, we introduce a novel regularized transfer learning framework for low-shot detection, where the transfer knowledge (TK) and background depression (BD) regularizations are proposed to leverage object knowledge respectively from source and target domains, in order to further enhance fine-tuning with a few target images. Finally, we examine our LSTD on a number of challenging low-shot detection experiments, where LSTD outperforms other state-of-the-art approaches. The results demonstrate that LSTD is a preferable deep detector for low-shot scenarios.
URL标识	查看原文
内容类型	会议论文
源URL	[http://ir.siat.ac.cn:8080/handle/172644/13684]
专题	深圳先进技术研究院_集成所
推荐引用方式 GB/T 7714	Hao Chen,Yali Wang,Guoyou Wang,et al. LSTD: A Low-Shot Transfer Detector for Object Detection[C]. 见:. 美国. 2018.

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。