.png){kind=icon}
返回
Progressive Object Transfer Detection
.png){kind=icon}
OA
AI
DOI：10.1109/TIP.2019.2938680.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Recent development of object detection mainly depends on deep learning with large-scale benchmarks. However, collecting such fully-annotated data is often difficult or expensive for real-world applications, which restricts the power of deep neural networks in practice. Alternatively, humans can detect new objects with little annotation burden, since humans often use the prior knowledge to identify new objects with few elaborately-annotated examples, and subsequently generalize this capacity by exploiting objects from wild images. Inspired by this procedure of learning to detect, we propose a novel Progressive Object Transfer Detection (POTD) framework. Specifically, we make three main contributions in this paper. First, POTD can leverage various object supervision of different domains effectively into a progressive detection procedure. Via such human-like learning, one can boost a target detection task with few annotations. Second, POTD consists of two delicate transfer stages, i.e., Low-Shot Transfer Detection (LSTD), and Weakly-Supervised Transfer Detection (WSTD). In LSTD, we distill the implicit object knowledge of source detector to enhance target detector with few annotations. It can effectively warm up WSTD later on. In WSTD, we design a recurrent object labelling mechanism for learning to annotate weakly-labeled images. More importantly, we exploit the reliable object supervision from LSTD, which can further enhance the robustness of target detector in the WSTD stage. Finally, we perform extensive experiments on a number of challenging detection benchmarks with different settings. The results demonstrate that, our POTD outperforms the recent state-of-the-art approaches. The codes and models are available at https://github.com/Cassie94/LSTD/tree/lstd.
Keyword:
Detectors
Object detection
Proposals
Task analysis
Benchmark testing
Deep learning
Labeling
Object detection
deep learning
transfer learning
weakly
semi-supervised detection
low-shot learning
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
13.7
论文数:
1.1W
被引数:
8.4W
机构
引用论文
.png){kind=icon}
Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系？
PREAI
分享收藏
Thermophysical Properties of Undercooled Alloys: An Overview of the Molecular Simulation ApproachesOAAI
OAAI分享收藏Using the Unified Protocol for Transdiagnostic Treatment of Emotional Disorders With Youth Exhibiting Anger and Irritability使用统一的协议对表现出愤怒和易怒的年轻人进行情绪障碍的诊断治疗
PREAI
分享收藏
查看更多内容