Self-Supervised Keypoint Detection Based on Multi-Layer Random Forest Regressor

Kim, Sangwon; Jeong, Mira; Ko, Byoung Chul

doi:10.1109/access.2021.3065022

Cited by 11 publications

(2 citation statements)

References 28 publications

(51 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a replacement for deeper and wider networks, the LMRF model is applied to an embedded system in low-power and low-memory in-vehicle systems for the monitoring of driver emotions. LMRF was also used as an image registration application for real-time keypoints matching in [ 27 ].…”

Section: Related Studiesmentioning

confidence: 99%

Model Simplification of Deep Random Forest for Real-Time Applications of Various Sensor Data

Kim

Nam

2021

Sensors

Self Cite

View full text Add to dashboard Cite

The deep random forest (DRF) has recently gained new attention in deep learning because it has a high performance similar to that of a deep neural network (DNN) and does not rely on a backpropagation. However, it connects a large number of decision trees to multiple layers, thereby making analysis difficult. This paper proposes a new method for simplifying a black-box model of a DRF using a proposed rule elimination. For this, we consider quantifying the feature contributions and frequency of the fully trained DRF in the form of a decision rule set. The feature contributions provide a basis for determining how features affect the decision process in a rule set. Model simplification is achieved by eliminating unnecessary rules by measuring the feature contributions. Consequently, the simplified and transparent DRF has fewer parameters and rules than before. The proposed method was successfully applied to various DRF models and benchmark sensor datasets while maintaining a robust performance despite the elimination of a large number of rules. A comparison with state-of-the-art compressed DNNs also showed the proposed model simplification’s higher parameter compression and memory efficiency with a similar classification accuracy.

show abstract

Section: Related Studiesmentioning

confidence: 99%

Model Simplification of Deep Random Forest for Real-Time Applications of Various Sensor Data

Kim

Nam

2021

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Traditionally, masterpiece machine learning modes with multi-spatial input features such as Random Forest [3], Adaboost [4], or SVM [5], to achieve object detection that has used to conclude knowledge model mining. However, before the detection step, Haar [6], SIFT [7], or HOG [8] adopted image feature extraction operations to establish the input features.…”

Section: Introductionmentioning

confidence: 99%

An Embedding Skeleton for Fish Detection and Marine Organisms Recognition

Zhu

Weng

et al. 2022

Symmetry

View full text Add to dashboard Cite

The marine economy has become a new growth point of the national economy, and many countries have started to implement the marine ranch project and made the project a new strategic industry to support vigorously. In fact, with the continuous improvement of people’s living standards, the market demand for precious seafood such as fish, sea cucumbers, and sea urchins increases. Shallow sea aquaculture has extensively promoted the vigorous development of marine fisheries. However, traditional diving monitoring and fishing are not only time consuming but also labor intensive; moreover, the personal injury is significant and the risk factor is high. In recent years, underwater robots’ development has matured and has been applied in other technologies. Marine aquaculture energy and chemical construction is a new opportunity for growth. The detection of marine organisms is an essential part of the intelligent strategy in marine ranch, which requires an underwater robot to detect the marine organism quickly and accurately in the complex ocean environment. This paper proposes a method called YOLOv4-embedding, based on one-stage deep learning arithmetic to detect marine organisms, construct a real-time target detection system for marine organisms, extract the in-depth features, and improve the backbone’s architecture and the neck connection. Compared with other object detection arithmetics, the YOLOv4-embedding object detection arithmetic was better at detection accuracy—with higher detection confidence and higher detection ratio than other one-stage object detection arithmetics, such as EfficientDet-D3. The results show that the suggested method could quickly detect different varieties in marine organisms. Furthermore, compared to the original YOLOv4, the mAP75 of the proposed YOLOv4-embedding improves 2.92% for the marine organism dataset at a real-time speed of 51 FPS on an RTX 3090.

show abstract

Image Registration Between Real Image and Virtual Image Based on Self-supervised Keypoint Learning

Kim,

Jang,

2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Self-Supervised Keypoint Detection Based on Multi-Layer Random Forest Regressor

Cited by 11 publications

References 28 publications

Model Simplification of Deep Random Forest for Real-Time Applications of Various Sensor Data

Model Simplification of Deep Random Forest for Real-Time Applications of Various Sensor Data

An Embedding Skeleton for Fish Detection and Marine Organisms Recognition

Image Registration Between Real Image and Virtual Image Based on Self-supervised Keypoint Learning

Contact Info

Product

Resources

About