Self-supervised monocular depth estimation based on combining convolution and multilayer perceptron

Zheng, Qiumei; Yu, Tao; Wang, Fenghua

doi:10.1016/j.engappai.2022.105587

Cited by 7 publications

(2 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By studying the interpretable relationship between the biological visual system and the monocular depth estimation network, it concretizes the attention mechanism in biological vision. Finally, Zheng et al 30 . designed a new framework, A hybrid of a Convolution, self-attention, and an Multilayer Perceptron (MLP) 31 network (CSMHNet), by combining decomposed large kernel convolutions and multi-layer perceptron to overcome the shortcomings of convolutional static weights and locality, while significantly reducing memory overhead compared to the Transformer architecture.…”

Section: Related Workmentioning

confidence: 97%

Dense monocular depth estimation for stereoscopic vision based on pyramid transformer and multi-scale feature fusion

Xia,

Wu,

Wang

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Stereoscopic display technology plays a significant role in industries, such as film, television and autonomous driving. The accuracy of depth estimation is crucial for achieving high-quality and realistic stereoscopic display effects. In addressing the inherent challenges of applying Transformers to depth estimation, the Stereoscopic Pyramid Transformer-Depth (SPT-Depth) is introduced. This method utilizes stepwise downsampling to acquire both shallow and deep semantic information, which are subsequently fused. The training process is divided into fine and coarse convergence stages, employing distinct training strategies and hyperparameters, resulting in a substantial reduction in both training and validation losses. In the training strategy, a shift and scale-invariant mean square error function is employed to compensate for the lack of translational invariance in the Transformers. Additionally, an edge-smoothing function is applied to reduce noise in the depth map, enhancing the model's robustness. The SPT-Depth achieves a global receptive field while effectively reducing time complexity. In comparison with the baseline method, with the New York University Depth V2 (NYU Depth V2) dataset, there is a 10% reduction in Absolute Relative Error (Abs Rel) and a 36% decrease in Root Mean Square Error (RMSE). When compared with the state-of-the-art methods, there is a 17% reduction in RMSE.

show abstract

Section: Related Workmentioning

confidence: 97%

Dense monocular depth estimation for stereoscopic vision based on pyramid transformer and multi-scale feature fusion

Xia,

Wu,

Wang

et al. 2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…This framework was integrated with parameter optimization algorithms to improve model accuracy without the need to adjust relevant parameters manually. Other models, namely multilayer perceptron (MLP) [13], random forest [14], support vector classification (SVC) [15], AdaBoost [16], and XGBoost [17], were also used for model training and were used in evaluations of the proposed transfer-learning model. The results of this study were also compared with the prediction results of [18] and [7], which were based on the same dataset.…”

Section: Introductionmentioning

confidence: 99%

Optimized Transfer Learning Based Dementia Prediction System for Rehabilitation Therapy Planning

Kuo

Huang

Yao

2023

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

Dementia is a neurodegenerative disease that causes a progressive deterioration of thinking, memory, and the ability to perform daily tasks. Other common symptoms include emotional disorders, language disorders, and reduced mobility; however, self-consciousness is unaffected. Dementia is irreversible, and medicine can only slow but not stop the degeneration. However, if dementia could be predicted, its onset may be preventable. Thus, this study proposes a revolutionary transfer-learning machine-learning model to predict dementia from magnetic resonance imaging data. In training, k-fold cross-validation and various parameter optimization algorithms were used to increase prediction accuracy. Synthetic minority oversampling was used for data augmentation. The final model achieved an accuracy of 90.7%, superior to that of competing methods on the same data set. This study's model facilitates the early diagnosis of dementia, which is key to arresting neurological deterioration from the disease, and is useful for underserved regions where many do not have access to a human physician. In the future, the proposed system can be used to plan rehabilitation therapy programs for patients.

show abstract

Monocular depth estimation via cross-spectral stereo information fusion

Liu

2024

Multimed Tools Appl

View full text Add to dashboard Cite

Self-supervised monocular depth estimation based on combining convolution and multilayer perceptron

Cited by 7 publications

References 46 publications

Dense monocular depth estimation for stereoscopic vision based on pyramid transformer and multi-scale feature fusion

Dense monocular depth estimation for stereoscopic vision based on pyramid transformer and multi-scale feature fusion

Optimized Transfer Learning Based Dementia Prediction System for Rehabilitation Therapy Planning

Monocular depth estimation via cross-spectral stereo information fusion

Contact Info

Product

Resources

About