EfficientNet-B0 Based Monocular Dense-Depth Map Estimation

Tadepalli, Yasasvy; Kollati, Meenakshi; Kuraparthi, Swaraja; Kora, Padmavathi

doi:10.18280/ts.380524

Cited by 12 publications

(6 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast, ResNet50 features a deeper network structure [29], demanding higher computational resources. The EfficientNet-B0 algorithm stands out for its heightened computational efficiency [30]. SENet [31], akin to ResNet in its fundamental structure, introduces an attention mechanism to enhance the network's sensitivity to vital features.…”

Section: Model Performance Comparison and Analysismentioning

confidence: 99%

A Lithology Recognition Network Based on Attention and Feature Brownian Distance Covariance

Zheng,

Liu,

Chen

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

In the context of mountain tunnel mining through the drilling and blasting method, the recognition of lithology from palm face images is crucial for the comprehensive analysis of geological conditions and the prevention of geological risks. However, the complexity of the background in the acquired palm face images, coupled with an insufficient data sample size, poses challenges. While the incorporation of deep learning technology has enhanced lithology recognition accuracy, issues persist, including inadequate feature extraction and suboptimal recognition accuracy. To address these challenges, this paper proposes a lithology recognition network integrating attention mechanisms and a feature Brownian distance covariance approach. Drawing inspiration from the Brownian distance covariance concept, a feature Brownian distance covariance module is devised to enhance the network's attention to rock sample features and improve classification accuracy. Furthermore, an enhanced lightweight Convolutional Block Attention Module is introduced, with upgrades to the multilayer perceptron in the channel attention module. These improvements emphasize attention to lithological features while mitigating interference from background information. The proposed method is evaluated on a palm face image dataset collected in the field. The proposed method was evaluated on a dataset comprising field-collected images of a tunnel rock face. The results illustrate a significant enhancement in the improved model's ability to recognize rock images, as evidenced by improvements across all objective evaluation metrics. The achieved accuracy rate of 97.60% surpasses that of the current mainstream lithology recognition neural network.

show abstract

Section: Model Performance Comparison and Analysismentioning

confidence: 99%

A Lithology Recognition Network Based on Attention and Feature Brownian Distance Covariance

Zheng,

Liu,

Chen

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…In the study by I.Laina et al [1], FCN based on ResNet is developed for depth estimation and they also proposed a loss function suitable for depth estimation. Yasasvy Tadepalli et al [2] developed an estimation model based on Efficient Net. Additionally, generative models such as GAN and Diffusion model are also applied to depth estimation [3][4].…”

Section: Related Workmentioning

confidence: 99%

“…Moreover, it offers a cost-effective alternative to depth measurement compared to often expensive sensors like LiDAR. Previous research has achieved significant accuracy improvements by leveraging stateof-the-art models like ResNet [1]or EfficientNet [2] and others [3] [4]. for estimation.…”

Section: Introductionmentioning

confidence: 99%

Monocular Depth Estimation Using a Deep Learning Model with Pre-Depth Estimation based on Size Perspective

Asano,

Yasumura

2023

Artificial Intelligence and Applications

View full text Add to dashboard Cite

In this paper, For the task of the depth map of a scene given a single RGB image. We present an estimation method using a deep learning model that incorporates size perspective (size constancy cues). By utilizing a size perspective, the proposed method aims to address the difficulty of depth estimation tasks which stems from the limited correlation between the information inherent to objects in RGB images (such as shape and color) and their corresponding depths. The proposed method consists of two deep learning models, a size perspective model and a depth estimation model, The size-perspective model plays a role like that of the size perspective and estimates approximate depths for each object in the image based on the size of the object's bounding box and its actual size. Based on these rough depth estimation (pre-depth estimation) results, A depth image representing through depths of each object (pre-depth image) is generated and this image is input with the RGB image into the depth estimation model. The pre-depth image is used as a hint for depth estimation and improves the performance of the depth estimation model. With the proposed method, it becomes possible to obtain depth inputs for the depth estimation model without using any devices other than a monocular camera be forehand. The proposed method contributes to the improvement in accuracy when there are objects present in the image that can be detected by the object detection model. In the experiments using an original indoor scene dataset, the proposed method demonstrated improvement in accuracy compared to the method without pre-depth images.

show abstract

“…By combining the three factors in the architecture, the coefficient calculation formula is as follows [48], [49]: where, with can be used to scale network width, depth, and resolution coefficients. While value can be used to determine the number of effective resource extension models.…”

Section: F Efficientnetmentioning

confidence: 99%

Automated Classification of Multiclass Brain Tumor MRI Images using Enhanced Deep Learning Technique

Razi,

Bustamam,

Latifah

et al. 2023

IJACSA

View full text Add to dashboard Cite

The brain is a vital organ, and the brain tumor is one of the most dangerous types of tumors in the world. Neuroimaging is an interesting and important discussion in diagnosing central nervous system tumors. Brain tumors have several types, namely meningioma, glioma, pituitary, schwannoma, and neurocytoma. A radiologist uses magnetic resonance imaging (MRI) to detect brain tumors because of its advantages over computed tomography. However, classifying multiclass MRI is difficult and takes a long time. This study proposes an automated classification of multiclass brain tumors using enhanced deep learning techniques. Various models are used in this research, namely VGG16, NasNet-Mobile, InceptionV3, ResNet50, and EfficientNet. For EfficientNet, we applied EfficientNet-B0-B7. From the experiments, EfficientNet-B2 is the superior, with the highest level of training accuracy of 99.90%, testing accuracy of 99.55%, precision of 99.50%, recall of 99.67%, and F1-Score of 99.58% with a training time of 15 minutes. The development of this automatic classification can assist radiologists in classifying brain tumor types more efficiently.

show abstract

EfficientNet-B0 Based Monocular Dense-Depth Map Estimation

Cited by 12 publications

References 23 publications

A Lithology Recognition Network Based on Attention and Feature Brownian Distance Covariance

A Lithology Recognition Network Based on Attention and Feature Brownian Distance Covariance

Monocular Depth Estimation Using a Deep Learning Model with Pre-Depth Estimation based on Size Perspective

Automated Classification of Multiclass Brain Tumor MRI Images using Enhanced Deep Learning Technique

Contact Info

Product

Resources

About