Automatic target recognition with deep metric learning.

Bouzid, Abdelhamid

doi:10.18297/etd/3501

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, deep learning has demonstrated remarkable performance in various machine learning tasks, including image classification, image embedding, and multiple object tracking (MOT). The superior representational power of deep learning in extracting highly abstract non-linear features has resulted in the emergence of a new research area known as Deep Metric Learning (DML) [9,[18][19][20]. This field aims to learn a mapping function that quantifies the similarity between data points, with the objective of minimizing the similarity between data points from the same category and maximizing the distance between data points from different categories.…”

Section: Deep Metric Learningmentioning

confidence: 99%

An Integrated vMF Embedding and VOS Framework for Robust Pedestrian Re-Identification and Out-of-Distribution Detection

Bouzid¹,

Sierra-Sosa²,

Elmaghraby³

2023

Preprint

View full text Add to dashboard Cite

In recent years, pedestrian re-identification has gained a lot of interest due to its importance for many purposes such as security and safety. Many types of solutions have been proposed to solve this problem, where the majority are based on a features extraction such Convolution Neural Networks (CNNs). These approaches assume that only the identities that are in the training data can be recognized. The pedestrians in the training data are called In distribution (ID). However, in real world scenarios, new pedestrians and objects can appear in the scene and the model should detect them as Out Of Distribution (OOD). In our previous study , we proposed a pedestrian re-identification based on von-Mises Fisher (vMF) distribution. Each identity is embedded in the unit sphere as a compact vMF distribution far from other identities distributions. The embedding is done through a base CNN. Recently, proposed a framework called Virtual Outlier Synthetic (VOS), that detects OOD based on synthesising virtual outlier in the embedding space in an online manner. Their approach assumes that the samples from the same object maps to a compact space. This assumption aligns with the vMF based approach. Therefore, in this paper, we revisited the vMF approach and merged with VOS in order to detect OOD data points. We present our approach to merge both frameworks. We conducted several experiments to evaluate our proposed framework. Results showed that our framework was able to detect new pedestrian that do not exist in the training data in the inference phase. It also slightly helped to improve the re-identification performance.

show abstract

Section: Deep Metric Learningmentioning

confidence: 99%

An Integrated vMF Embedding and VOS Framework for Robust Pedestrian Re-Identification and Out-of-Distribution Detection

Bouzid¹,

Sierra-Sosa²,

Elmaghraby³

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In recent years, deep learning has demonstrated remarkable performance in various machine learning tasks, including image classification, image embedding, and multiple object tracking (MOT). The superior representational power of deep learning in extracting highly abstract non-linear features has resulted in the emergence of a new research area known as Deep Metric Learning (DML) [17,[27][28][29]. This field aims to learn a mapping function that quantifies the similarity between data points, with the objective of minimizing the similarity between data points from the same category and maximizing the distance between data points from different categories.…”

Section: Deep Metric Learningmentioning

confidence: 99%

A Robust Pedestrian Re-Identification and Out-Of-Distribution Detection Framework

Bouzid

Sierra-Sosa

Elmaghraby

2023

Drones

View full text Add to dashboard Cite

Pedestrian re-identification is an important field due to its applications in security and safety. Most current solutions for this problem use CNN-based feature extraction and assume that only the identities that are in the training data can be recognized. On the one hand, the pedestrians in the training data are called In-Distribution (ID). On the other hand, in real-world scenarios, new pedestrians and objects can appear in the scene, and the model should detect them as Out-Of-Distribution (OOD). In our previous study, we proposed a pedestrian re-identification based on von Mises–Fisher (vMF) distribution. Each identity is embedded in the unit sphere as a compact vMF distribution far from other identity distributions. Recently, a framework called Virtual Outlier Synthetic (VOS) was proposed, which detects OOD based on synthesizing virtual outliers in the embedding space in an online manner. Their approach assumes that the samples from the same object map to a compact space, which aligns with the vMF-based approach. Therefore, in this paper, we revisited the vMF approach and merged it with VOS to detect OOD data points. Experiment results showed that our framework was able to detect new pedestrians that do not exist in the training data in the inference phase. Furthermore, this framework improved the re-identification performance and holds a significant potential in real-world scenarios.

show abstract

Automatic target recognition with deep metric learning.

Cited by 2 publications

References 0 publications

An Integrated vMF Embedding and VOS Framework for Robust Pedestrian Re-Identification and Out-of-Distribution Detection

An Integrated vMF Embedding and VOS Framework for Robust Pedestrian Re-Identification and Out-of-Distribution Detection

A Robust Pedestrian Re-Identification and Out-Of-Distribution Detection Framework

Contact Info

Product

Resources

About