Few-Shot Object Detection: A Comprehensive Survey

Köhler, Mona; Eisenbach, Markus; Groß, Horst–Michael

doi:10.1109/tnnls.2023.3265051

Cited by 37 publications

(12 citation statements)

References 139 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast, few-shot object detection (FSOD) [15][16][17] provides a solution designed to be able to quickly detect new objects from a very small number of annotated samples of new classes. FSOD is generally divided into two phases.…”

Section: Of 18mentioning

confidence: 99%

A Few-Shot Object Detection Method for Endangered Species

Yan,

Ruan,

Zhu

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Endangered species detection plays an important role in biodiversity conservation and is significant in maintaining ecological balance. Existing deep learning-based object detection methods are overly dependent on a large number of supervised samples, and building such endangered species datasets is usually costly. Aiming at the problems faced by endangered species detection, such as low accuracy and easy loss of location information, an efficient endangered species detection method with fewer samples is proposed to extend the few-shot object detection technique to the field of endangered species detection, which requires only a small number of training samples to obtain excellent detection results. First, SE-Res2Net is proposed to optimize the feature extraction capability. Secondly, an RPN network with multiple attention mechanism is proposed. Finally, for the classification confusion problem, a weighted prototype-based comparison branch is introduced to construct weighted category prototype vectors, which effectively improves the performance of the original classifier. Under the setting of 30 samples in the endangered species dataset, the average detection accuracy value of the method, mAP50, reaches 76.54%, which is 7.98% higher than that of the pre-improved FSCE method. This paper also compares the algorithm on the PASCOL VOC dataset, which is optimal and has good generalization ability compared to the other five algorithms.

show abstract

Section: Of 18mentioning

confidence: 99%

A Few-Shot Object Detection Method for Endangered Species

Yan,

Ruan,

Zhu

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…This initial model is then further trained on a base dataset, yielding what is known as a base model. Many methodologies then extend this by training on the base model data, including new classes, culminating in the final iteration of the model [32].…”

Section: Implementation Code For Faster R-cnnmentioning

confidence: 99%

Comparison of Machine Learning Approaches for Robust and Timely Detection of PPE in Construction Sites

Azizi,

Koskinopoulou,

Petillot

2024

Robotics

View full text Add to dashboard Cite

Globally, workplace safety is a critical concern, and statistics highlight the widespread impact of occupational hazards. According to the International Labour Organization (ILO), an estimated 2.78 million work-related fatalities occur worldwide each year, with an additional 374 million non-fatal workplace injuries and illnesses. These incidents result in significant economic and social costs, emphasizing the urgent need for effective safety measures across industries. The construction sector in particular faces substantial challenges, contributing a notable share to these statistics due to the nature of its operations. As technology, including machine vision algorithms and robotics, continues to advance, there is a growing opportunity to enhance global workplace safety standards and mitigate the human toll of occupational hazards on a broader scale. This paper explores the development and evaluation of two distinct algorithms designed for the accurate detection of safety equipment on construction sites. The first algorithm leverages the Faster R-CNN architecture, employing ResNet-50 as its backbone for robust object detection. Subsequently, the results obtained from Faster R-CNN are compared with those of the second algorithm, Few-Shot Object Detection (FsDet). The selection of FsDet is motivated by its efficiency in addressing the time-intensive process of compiling datasets for network training in object recognition. The research methodology involves training and fine-tuning both algorithms to assess their performance in safety equipment detection. Comparative analysis aims to evaluate the effectiveness of novel training methods employed in the development of these machine vision algorithms.

show abstract

“…Extensions to explainable classifiers using heterogeneous transfer learning and open-set domain adaptation paradigms can be a possible future avenue to explore. Few Shot Learning [166,167] aims to learn classifiers from fewer examples by leveraging features learned from related classes having a larger number of instances. For instance, a zebra can be considered as an animal with a horse-like body and tiger-like stripes.…”

Section: Future Workmentioning

confidence: 99%

Explainable Image Classification: The Journey So Far and the Road Ahead

Kamakshi,

Krishnan

2023

View full text Add to dashboard Cite

Explainable Artificial Intelligence (XAI) has emerged as a crucial research area to address the interpretability challenges posed by complex machine learning models. In this survey paper, we provide a comprehensive analysis of existing approaches in the field of XAI, focusing on the tradeoff between model accuracy and interpretability. Motivated by the need to address this tradeoff, we conduct an extensive review of the literature, presenting a multi-view taxonomy that offers a new perspective on XAI methodologies. We analyze various sub-categories of XAI methods, considering their strengths, weaknesses, and practical challenges. Moreover, we explore causal relationships in model explanations and discuss approaches dedicated to explaining cross-domain classifiers. The latter is particularly important in scenarios where training and test data are sampled from different distributions. Drawing insights from our analysis, we propose future research directions, including exploring explainable allied learning paradigms, developing evaluation metrics for both traditionally trained and allied learning-based classifiers, and applying neural architectural search techniques to minimize the accuracy–interpretability tradeoff. This survey paper provides a comprehensive overview of the state-of-the-art in XAI, serving as a valuable resource for researchers and practitioners interested in understanding and advancing the field.

show abstract

Few-Shot Object Detection: A Comprehensive Survey

Cited by 37 publications

References 139 publications

A Few-Shot Object Detection Method for Endangered Species

A Few-Shot Object Detection Method for Endangered Species

Comparison of Machine Learning Approaches for Robust and Timely Detection of PPE in Construction Sites

Explainable Image Classification: The Journey So Far and the Road Ahead

Contact Info

Product

Resources

About