Few-Shot Object Detection: Research Advances and Challenges

2024-04-07 · Zhimeng Xin, Shiming Chen, Tianxu Wu, Yuanjie Shao, Weiping Ding, Xinge You

Object detection as a subfield within computer vision has achieved remarkable progress, which aims to accurately identify and locate a specific object from images or videos. Such methods rely on large-scale labeled training samples for each object category to ensure accurate detection, but obtaining extensive annotated data is a labor-intensive and expensive process in many real-world scenarios. To tackle this challenge, researchers have explored few-shot object detection (FSOD) that combines few-shot learning and object detection techniques to rapidly adapt to novel objects with limited annotated samples. This paper presents a comprehensive survey to review the significant advancements in the field of FSOD in recent years and summarize the existing challenges and solutions. Specifically, we first introduce the background and definition of FSOD to emphasize potential value in advancing the field of computer vision. We then propose a novel FSOD taxonomy method and survey the plentifully remarkable FSOD algorithms based on this fact to report a comprehensive overview that facilitates a deeper understanding of the FSOD problem and the development of innovative solutions. Finally, we discuss the advantages and limitations of these algorithms to summarize the challenges, potential research direction, and development trend of object detection in the data scarcity scenario.

📄 PDF Abstract BibTeX arXiv:2404.04799

Code (0)

등록된 구현이 없습니다.

Tasks

Few-Shot Learning Few-Shot Object DetectionObjectobject-detection Object DetectionSurvey

TIDE: Test Time Few Shot Object Detection

2023-11-30 · Weikai Li, Hongfeng Wei, Yanlai Wu, Jie Yang 외

Few-shot object detection (FSOD) aims to extract semantic knowledge from limited object instances of novel categories within a target domain. Recent advances in FSOD focus on fine-tuning the base model based on a few obj…

Data Augmentation Few-Shot Object Detection Meta-Learning Object+2

Comparison Network for One-Shot Conditional Object Detection

2019-04-04 · Tengfei Zhang, Yue Zhang, Xian Sun, Hao Sun 외

The current advances in object detection depend on large-scale datasets to get good performance. However, there may not always be sufficient samples in many scenarios, which leads to the research on few-shot detection as…

Object object-detection Object Detection

Leveraging Bottom-Up and Top-Down Attention for Few-Shot Object Detection

2020-07-23 · Xianyu Chen, Ming Jiang, Qi Zhao

Few-shot object detection aims at detecting objects with few annotated examples, which remains a challenging research problem yet to be explored. Recent studies have shown the effectiveness of self-learned top-down atten…

Few-Shot Learning Few-Shot Object Detection Object object-detection+1

A Survey of Deep Learning for Low-Shot Object Detection

2021-12-06 · Qihan Huang, Haofei Zhang, Mengqi Xue, Jie Song 외

Object detection has achieved a huge breakthrough with deep neural networks and massive annotated data. However, current detection methods cannot be directly transferred to the scenario where the annotated data is scarce…

Deep Learning Few-Shot Learning Few-Shot Object Detection image-classification+8

Recent Few-Shot Object Detection Algorithms: A Survey with Performance Comparison

2022-03-27 · Tianying Liu, Lu Zhang, Yang Wang, Jihong Guan 외

The generic object detection (GOD) task has been successfully tackled by recent deep neural networks, trained by an avalanche of annotated training samples from some common classes. However, it is still non-trivial to ge…

Articles Few-Shot Object Detection Meta-Learning Object+3