Deep Residual Learning for Image Recognition: A Survey

Shafiq, Muhammad; Gu, Zhaoquan

doi:10.3390/app12188972

Cited by 289 publications

(145 citation statements)

References 84 publications

Supporting

Mentioning

144

Contrasting

Unclassified

Order By: Relevance

“…Figure 17 is a demonstration of live testing. Because the object is not moving in this type of static object detection module testing, the system successfully detected the objects and recognized the detected object classes ( Shafiq et al, 2020 ; Shafiq and Gu, 2022 ; Wahab et al, 2022 ).…”

Section: Experimental Results and Evaluationmentioning

confidence: 99%

Design and implementation of real-time object detection system based on single-shoot detector and OpenCV

Wahab

Ullah²,

Shah³

et al. 2022

Front. Psychol.

View full text Add to dashboard Cite

Computer vision (CV) and human–computer interaction (HCI) are essential in many technological fields. Researchers in CV are particularly interested in real-time object detection techniques, which have a wide range of applications, including inspection systems. In this study, we design and implement real-time object detection and recognition systems using the single-shoot detector (SSD) algorithm and deep learning techniques with pre-trained models. The system can detect static and moving objects in real-time and recognize the object’s class. The primary goals of this research were to investigate and develop a real-time object detection system that employs deep learning and neural systems for real-time object detection and recognition. In addition, we evaluated the free available, pre-trained models with the SSD algorithm on various types of datasets to determine which models have high accuracy and speed when detecting an object. Moreover, the system is required to be operational on reasonable equipment. We tried and evaluated several deep learning structures and techniques during the coding procedure and developed and proposed a highly accurate and efficient object detection system. This system utilizes freely available datasets such as MS Common Objects in Context (COCO), PASCAL VOC, and Kitti. We evaluated our system’s accuracy using various metrics such as precision and recall. The proposed system achieved a high accuracy of 97% while detecting and recognizing real-time objects.

show abstract

Section: Experimental Results and Evaluationmentioning

confidence: 99%

Design and implementation of real-time object detection system based on single-shoot detector and OpenCV

Wahab

Ullah²,

Shah³

et al. 2022

Front. Psychol.

View full text Add to dashboard Cite

show abstract

“…Each Transformer block includes two sub-blocks: multi-head self-attention mechanism and position-wise feed-forward networks. In addition, each sub-block also includes layer normalization modules [ 39 ] and residual connectors [ 40 ]. Transformer blocks can be used in a different field.…”

Section: Methodsmentioning

confidence: 99%

“…We also applied GLU to the Attention sub-block, as shown in Figure 4 . Here, we used the residual connection [ 40 ] to fuse the context information through the self-attention module, which can improve the stability of the model. The fused information is passed through GLU to improve the performance of the Attention sub-block.…”

Section: Methodsmentioning

confidence: 99%

Driving Fatigue Detection with Three Non-Hair-Bearing EEG Channels and Modified Transformer Model

Wang

Tian

et al. 2022

Entropy

View full text Add to dashboard Cite

Driving fatigue is the main cause of traffic accidents, which seriously affects people’s life and property safety. Many researchers have applied electroencephalogram (EEG) signals for driving fatigue detection to reduce negative effects. The main challenges are the practicality and accuracy of the EEG-based driving fatigue detection method when it is applied on the real road. In our previous study, we attempted to improve the practicality of fatigue detection based on the proposed non-hair-bearing (NHB) montage with fewer EEG channels, but the recognition accuracy was only 76.47% with the random forest (RF) model. In order to improve the accuracy with NHB montage, this study proposed an improved transformer architecture for one-dimensional feature vector classification based on introducing the Gated Linear Unit (GLU) in the Attention sub-block and Feed-Forward Networks (FFN) sub-block of a transformer, called GLU-Oneformer. Moreover, we constructed an NHB-EEG-based feature set, including the same EEG features (power ratio, approximate entropy, and mutual information (MI)) in our previous study, and the lateralization features of the power ratio and approximate entropy based on the strategy of brain lateralization. The results indicated that our GLU-Oneformer method significantly improved the recognition performance and achieved an accuracy of 86.97%. Our framework demonstrated that the combination of the NHB montage and the proposed GLU-Oneformer model could well support driving fatigue detection.

show abstract

“…The training process was set up to facilitate comparison between different models after undergoing end-to-end finetuning. Only ResNet50 was used for the backbones, as is standard in self-supervised model evaluation and as was used in both the NNCLR and SimCLR original papers [40, 41, 46]. Two backbones for the end-to-end process were chosen from a pretraining sweep with the mentioned self-supervised contrastive architectures, and one backbone was initialized with ImageNet weights.…”

Section: Methodsmentioning

confidence: 99%

Self-Supervised Maize Kernel Classification and Segmentation for Embryo Identification

Dong

Nagasubramanian

Wang

et al. 2022

Preprint

View full text Add to dashboard Cite

Computer vision and deep learning (DL) techniques have succeeded in a wide range of diverse fields. Recently, these techniques have been successfully deployed in plant science applications to address food security, productivity, and environmental sustainability problems for a growing global population. However, training these DL models often necessitates the large-scale manual annotation of data which frequently becomes a tedious and time-and-resource-intensive process. Recent advances in self-supervised learning (SSL) methods have proven instrumental in overcoming these obstacles, using purely unlabeled datasets to pre-train DL models. Here, we implement the popular self-supervised contrastive learning methods of NNCLR (Nearest neighbor Contrastive Learning of visual Representations) and SimCLR (Simple framework for Contrastive Learning of visual Representations) for the classification of spatial orientation and segmentation of embryos of maize kernels. Maize kernels are imaged using a commercial high-throughput imaging system. This image data is often used in multiple downstream applications across both production and breeding applications, for instance, sorting for oil content based on segmenting and quantifying the scutellum's size and for classifying haploid and diploid kernels. We show that in both classification and segmentation problems, SSL techniques outperform their purely supervised transfer learning-based counterparts and are significantly more annotation efficient. Additionally, we show that a single SSL pre-trained model can be efficiently finetuned for both classification and segmentation, indicating good transferability across multiple downstream applications. Segmentation models with SSL-pretrained backbones produce DICE similarity coefficients of 0.81, higher than the 0.78 and 0.73 of those with ImageNet-pretrained and randomly initialized backbones, respectively. We observe that finetuning classification and segmentation models on as little as 1% annotation produces competitive results. These results show SSL provides a meaningful step forward in data efficiency with agricultural deep learning and computer vision.

show abstract

Deep Residual Learning for Image Recognition: A Survey

Cited by 289 publications

References 84 publications

Design and implementation of real-time object detection system based on single-shoot detector and OpenCV

Design and implementation of real-time object detection system based on single-shoot detector and OpenCV

Driving Fatigue Detection with Three Non-Hair-Bearing EEG Channels and Modified Transformer Model

Self-Supervised Maize Kernel Classification and Segmentation for Embryo Identification

Contact Info

Product

Resources

About