An Efficient Deep Convolutional Neural Network for Semantic Segmentation

Olimov, Bekhzod; Kim, Jeonghong; Paul, Anand; Subramanian, Barathi

doi:10.1109/icot51877.2020.9468748

Cited by 7 publications

(3 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It insensitive to outliers that far from the center, and it effectively control the magnitude of the gradient, thereby preventing issues such as gradient explosion. The Smooth 1 L loss function has been widely used in tasks like bounding box regression for object detection [4], [5] and semantic segmentation [30], [31]. In the field of stereo matching methods based on CNNs, the disparity calculation applies fully differentiable soft argmin mechanism to obtain smooth disparity estimate, and it can also be seen as a dense regression problem in its own right.…”

Section: ) Supervised Learning Strategymentioning

confidence: 99%

GA-Stereo: A Real-Time Stereo Network Based on the Gradient Flow Shunting Strategy and the Atrous Pyramid Network

Jiao,

Wang,

Wang

et al. 2023

IEEE Access

View full text Add to dashboard Cite

While stereo matching methods have great progress in recent years, they still face several formidable challenges. These challenges mainly include how to fully utilize global context and depth semantic information for depth feature extraction while maintaining low computational cost, and how to accurately predict disparity in object details and ill-posed regions of stereo images. In this paper, we propose GA-Stereo, an end-to-end stereo network aiming at fast and more accurate disparity regression from rectified stereo images. Firstly, we propose GA-Net, a depth feature extraction network for stereo networks; it utilizes a gradient flow shunting strategy and aggregated residual transformation to calculate the matching cost of stereo images. Secondly, we propose an Atrous Pyramid Network, which implements convolution kernels adaptive sampling to assist the initial disparity map optimize, on the basis of more feature information and larger receptive field. Finally, we propose a collaborative supervised learning strategy. By using the collaborative supervised learning strategy during training stage, our GA-Stereo can not only calculate loss from the Ground Truth, but also calculate the loss from perceptual reconstruction loss and edge-loss smoothing loss to obtain better training results and more accurate predicted disparity map than other stereo networks. Our GA-Stereo achieve highly competitive results in matching accuracy and computational efficiency on stereo benchmarks, including SceneFlow, KITTI2012, and KITTI2015. This advancement represents a significant step forward in real-time stereo matching methods.

show abstract

Section: ) Supervised Learning Strategymentioning

confidence: 99%

GA-Stereo: A Real-Time Stereo Network Based on the Gradient Flow Shunting Strategy and the Atrous Pyramid Network

Jiao,

Wang,

Wang

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…[17][18][19][20][21][22][23][24][25] For better classification performance, accurate lesion area extraction is very important. [26][27][28][29][30] In this regard, Olimov et al 26 proposed an image segmentation model which provides better results by modifying the U-Net model. In another work, Olimov et al 27 proposed an efficient deep CNN model to extract lesion area using atrous and asymmetric convolution.…”

Section: Related Workmentioning

confidence: 99%

“…In this regard, CNN 15,16 quickly becomes a choice in examining dermoscopic images 17‐25 . For better classification performance, accurate lesion area extraction is very important 26‐30 . In this regard, Olimov et al 26 proposed an image segmentation model which provides better results by modifying the U‐Net model.…”

Section: Related Workmentioning

confidence: 99%

A customized deep learning framework for skin lesion classification using dermoscopic images

Sahoo

Dash

Mohapatra

2022

Computer Animation & Virtual

View full text Add to dashboard Cite

Automated analysis of skin lesions in dermoscopy images has gained much attention due to its medical importance in the early detection of melanoma. Detection of lesions has become a challenge due to the strong visual similarity between benign and malignant skin lesions. In this research, a customized deep convolutional neural network (CNN) architecture has been designed to discriminate between benign and malignant lesions. The model is designed carefully with lesser convolution layers, fewer filters, and parameters to achieve better classification performance compared to pretrained VGG16, ResNet50, InceptionV3 models and, ensures state‐of‐the‐art performance. The proposed model is composed of nine trainable layers: eight convolution layers and one fully connected layer. The suggested framework is extensively evaluated on the benchmark ISIC 2016 challenge dataset. The effect of different input transformations over the dataset has been studied. For fair comparison, standard deep learning models such as VGG16, ResNet50, and InceptionV3 have been used for lesion classification using transfer learning approach. The memory requirement of the proposed model is reduced by 388, 68, and 63 times and FLOPs needed are lowered by 95%, 85%, and 84% compared to VGG16‐TrL, ResNet50‐TrL, and InceptionV3‐TrL, respectively. Results show that class balancing with external images improves classification performance.

show abstract

An integrated mediapipe-optimized GRU model for Indian sign language recognition

Subramanian

Olimov

Naik

et al. 2022

Sci Rep

Self Cite

View full text Add to dashboard Cite

Sign language recognition is challenged by problems, such as accurate tracking of hand gestures, occlusion of hands, and high computational cost. Recently, it has benefited from advancements in deep learning techniques. However, these larger complex approaches cannot manage long-term sequential data and they are characterized by poor information processing and learning efficiency in capturing useful information. To overcome these challenges, we propose an integrated MediaPipe-optimized gated recurrent unit (MOPGRU) model for Indian sign language recognition. Specifically, we improved the update gate of the standard GRU cell by multiplying it by the reset gate to discard the redundant information from the past in one screening. By obtaining feedback from the resultant of the reset gate, additional attention is shown to the present input. Additionally, we replace the hyperbolic tangent activation in standard GRUs with exponential linear unit activation and SoftMax with Softsign activation in the output layer of the GRU cell. Thus, our proposed MOPGRU model achieved better prediction accuracy, high learning efficiency, information processing capability, and faster convergence than other sequential models.

show abstract

An Efficient Deep Convolutional Neural Network for Semantic Segmentation

Cited by 7 publications

References 29 publications

GA-Stereo: A Real-Time Stereo Network Based on the Gradient Flow Shunting Strategy and the Atrous Pyramid Network

GA-Stereo: A Real-Time Stereo Network Based on the Gradient Flow Shunting Strategy and the Atrous Pyramid Network

A customized deep learning framework for skin lesion classification using dermoscopic images

An integrated mediapipe-optimized GRU model for Indian sign language recognition

Contact Info

Product

Resources

About