DG-Labeler and DGL-MOTS Dataset: Boost the Autonomous Driving Perception

Cui, Yiming; Cao, Zhiwen; Xie, Yixin; Jiang, X. Y.; Tao, Feng; Chen, Yingjie; Li, Lin; Liu, Dongfang

doi:10.1109/wacv51458.2022.00347

Cited by 34 publications

(27 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, YOLOv5SCB is trained using the public dataset KITTI [11] . The effectiveness of the proposed module is demonstrated using ablation experiments.…”

Section: Experimental Results and Analysismentioning

confidence: 99%

The design of lightweight vehicle detection model based on improved YOLOv5

Jiang,

Wen,

Xie

et al. 2023

Third International Conference on Image Processing and Intelligent Control (IPIC 2023)

View full text Add to dashboard Cite

Convolutional neural network-based target detection algorithms are widely used in vehicle detection due to their high speed and accuracy. However, existing algorithms are characterized by large computational volumes, complex network structures, and severe resource constraints. They make them difficult to be ported to mobile platforms and embedded devices. Therefore, the structure of the relevant target detection algorithm needs to be optimized to enable wider deployment of the algorithm. To address the problems mentioned earlier, a YOLOv5SCB lightweight target detection network model is proposed. In the presented model, Shufflenetv2 and CA module are introduced into the backbone network to reduce the complexity of the network model and improve the detection accuracy of the model. Furthermore, BiFPN is integrated into the neck network to improve the efficiency of network feature fusion and enhance the ability of network feature expression. The experimental data show that compared with the original YOLOv5, the model parameters of the proposed YOLOv5SCB are reduced by 62.4% and the overall detection accuracy is improved by 1.1%.

show abstract

“…In this paper, YOLOv5SCB is trained using the public dataset KITTI [11] . The effectiveness of the proposed module is demonstrated using ablation experiments.…”

Section: Experimental Results and Analysismentioning

confidence: 99%

The design of lightweight vehicle detection model based on improved YOLOv5

Jiang,

Wen,

Xie

et al. 2023

Third International Conference on Image Processing and Intelligent Control (IPIC 2023)

View full text Add to dashboard Cite

show abstract

“…Additionally, a light gradient boosting machine (LGBM) is also widely used with outstanding performance [ 48 , 49 ] due to the advantages of fast training speed and high efficiency, accuracy, and capability to handle large-scale data [ 49 , 50 ]. Recently, deep learning (DL) algorithms (e.g., convolutional neural network (CNN)) have demonstrated superior prediction performance in the field of bioinformatics, such as in the prediction of modification sites on DNA, RNA, and proteins [ 26 , 27 , 31 , 51 , 52 , 53 ] and many domains of social relevance [ 54 , 55 , 56 , 57 , 58 , 59 , 60 , 61 , 62 ]…”

Section: Resultsmentioning

confidence: 99%

ResSUMO: A Deep Learning Architecture Based on Residual Structure for Prediction of Lysine SUMOylation Sites

Zhu

Liu²,

Chen

et al. 2022

Cells

View full text Add to dashboard Cite

Lysine SUMOylation plays an essential role in various biological functions. Several approaches integrating various algorithms have been developed for predicting SUMOylation sites based on a limited dataset. Recently, the number of identified SUMOylation sites has significantly increased due to investigation at the proteomics scale. We collected modification data and found the reported approaches had poor performance using our collected data. Therefore, it is essential to explore the characteristics of this modification and construct prediction models with improved performance based on an enlarged dataset. In this study, we constructed and compared 16 classifiers by integrating four different algorithms and four encoding features selected from 11 sequence-based or physicochemical features. We found that the convolution neural network (CNN) model integrated with residue structure, dubbed ResSUMO, performed favorably when compared with the traditional machine learning and CNN models in both cross-validation and independent tests. The area under the receiver operating characteristic (ROC) curve for ResSUMO was around 0.80, superior to that of the reported predictors. We also found that increasing the depth of neural networks in the CNN models did not improve prediction performance due to the degradation problem, but the residual structure could be included to optimize the neural networks and improve performance. This indicates that residual neural networks have the potential to be broadly applied in the prediction of other types of modification sites with great effectiveness and robustness. Furthermore, the online ResSUMO service is freely accessible.

show abstract

“…Moreover, incorporating external knowledge bases has been found to enhance the model's ability to generate factually accurate responses [13,14,15,16]. The use of multimodal data, integrating text with images or videos, has further been shown to improve the contextual understanding of those models [17,18,19]. Techniques for optimizing model architecture, such as attention mechanisms and transformer layers, have been pivotal in increasing the efficiency and accuracy of LLMs [20,8,21,22].…”

Section: Enhancing Llm Accuracymentioning

confidence: 99%

“…Adaptive learning rates and fine-tuning strategies have also been identified as crucial for tailoring models to specific tasks or domains, thereby improving their performance [8,14,23,24]. Lastly, the implementation of robust evaluation metrics enables a more nuanced assessment of model accuracy, guiding iterative improvements [17,25,14,26,16].…”

Section: Enhancing Llm Accuracymentioning

confidence: 99%

Equipping Llama with Google Query API for Improved Accuracy and Reduced Hallucination

Bae,

Kim,

Kim

2024

Preprint

View full text Add to dashboard Cite

This study investigates the integration of the Llama 2 7b large language model (LLM) with the Google Query API to enhance its accuracy and reduce hallucination instances. By leveraging real-time internet data, we aimed to address the limitations of static training datasets and improve the model's performance across various language processing tasks. The methodology involved augmenting Llama 2 7b's architecture to incorporate dynamic data retrieval from the Google Query API, followed by an evaluation of its impact on model accuracy and hallucination reduction using the BIG-Bench benchmark. The results indicate significant improvements in both accuracy and reliability, demonstrating the effectiveness of integrating LLMs with external data sources. This integration not only marks a substantial advancement in the capabilities of LLMs but also raises important considerations regarding data bias, privacy, and the ethical use of internet-sourced information. The study's findings contribute to the ongoing discourse on enhancing LLMs, suggesting a promising direction for future research and development in artificial intelligence.

show abstract

DG-Labeler and DGL-MOTS Dataset: Boost the Autonomous Driving Perception

Cited by 34 publications

References 36 publications

The design of lightweight vehicle detection model based on improved YOLOv5

The design of lightweight vehicle detection model based on improved YOLOv5

ResSUMO: A Deep Learning Architecture Based on Residual Structure for Prediction of Lysine SUMOylation Sites

Equipping Llama with Google Query API for Improved Accuracy and Reduced Hallucination

Contact Info

Product

Resources

About