Performance Analysis of Different Loss Function in Face Detection Architectures

Ferdous, Rezowan; Arifeen, Murshedul; Eiko, Tipu Sultan; Mamun, Shamim Al

doi:10.1007/978-981-33-4673-4_54

Cited by 5 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This model occupies storage of 87M and its reasoning speed is 26 targets per second. We compared the proposed knowledge distillation method with the other four classic technologies reported in recent years mentioned in Part 1, including: KD: knowledge distillation (Hinton et al, 2015); FitNet (Romero et al, 2014); SP: similarity preserving (Tung and Mori, 2019); CC: correlation congruence ; and CE: cross-entropy (Ferdous et al, 2020). Five neural networks with different parameter volumes and reasoning speeds were used as student networks.…”

Section: Experimental Results Of the Proposed Knowledge Distillation ...mentioning

confidence: 99%

Deep Learning for Marine Science

2024

Frontiers Research Topics

View full text Add to dashboard Cite

Deep learning (DL), mainly composed of deep and complex neural networks such as recurrent network and convolutional network, is an emerging research branch in the field of artificial intelligence and machine learning. DL revolution has a far-reaching impact on all scientific disciplines and every corner of our lives. With continuing technological advances, marine science is entering into the big data era with the exponential growth of information. DL is an effective means of harnessing the power of big data. Combined with unprecedented data from cameras, acoustic recorders, satellite remote sensing, and large model outputs, DL enables scientists to solve complex problems in biology, ecosystems, climate, energy, as well as physical and chemical interactions. Although DL has made great strides, it is still only beginning to emerge in many fields of marine science, especially towards representative applications and best practices for the automatic analysis of marine organisms and marine environments. DL in nowadays' marine science mainly leverages cutting-edge techniques of deep neural networks and massive data which collected by <i>in-situ</i> optical or acoustic imaging sensors for underwater applications, such as plankton classification and coral reef detection. This research topic aims to expand the applications of marine science to cover all aspects of detection, classification, segmentation, localization, and density estimation of marine objects, organisms, and phenomena.

show abstract

Section: Experimental Results Of the Proposed Knowledge Distillation ...mentioning

confidence: 99%

Deep Learning for Marine Science

2024

Frontiers Research Topics

View full text Add to dashboard Cite

show abstract

“…This model occupies storage of 87M and its reasoning speed is 26 targets per second. We compared the proposed knowledge distillation method with the other four classic technologies reported in recent years mentioned in Part 1, including: KD: knowledge distillation (Hinton et al, 2015); FitNet (Romero et al, 2014); SP: similarity preserving (Tung and Mori, 2019); CC: correlation congruence (Peng et al, 2019); and CE: cross-entropy (Ferdous et al, 2020). Five neural networks with different parameter volumes and reasoning speeds were used as student networks.…”

Section: Comparison With Classical Knowledge Distillation Methodsmentioning

confidence: 99%

Toward efficient deep learning system for in-situ plankton image recognition

Yue,

Chen,

Long

et al. 2023

Front. Mar. Sci.

View full text Add to dashboard Cite

Plankton is critical for the structure and function of marine ecosystems. In the past three decades, various underwater imaging systems have been developed to collect in-situ plankton images and image processing has been a major bottleneck that hinders the deployment of plankton imaging systems. In recent years, deep learning methods have greatly enhanced our ability of processing in-situ plankton images, but high-computational demands and longtime consumption still remain problematic. In this study, we used knowledge distillation as a framework for model compression and improved computing efficiency while maintaining original high accuracy. A novel inter-class similarity distillation algorithm based on feature prototypes was proposed and enabled the student network (small scale) to acquire excellent ability for plankton recognition after being guided by the teacher network (large scale). To identify the suitable teacher network, we compared emerging Transformer neural networks and convolution neural networks (CNNs), and the best performing deep learning model, Swin-B, was selected. Utilizing the proposed knowledge distillation algorithm, the feature extraction ability of Swin-B was transferred to five more lightweight networks, and the results had been evaluated in taxonomic dataset of in-situ plankton images. Subsequently, the chosen lightweight model and the Bilateral–Sobel edge enhancement were tested to process in-situ images with high level of noises captured from coastal waters of Guangdong, China and achieved an overall recall rate of 91.73%. Our work contributes to effective deep learning models and facilitates the deployment of underwater plankton imaging systems by promoting both accuracy and speed in recognition of plankton targets.

show abstract

“…Loss Function and Optimizer. The loss function is applied to evaluate the difference between the predicted and actual values of the model [33][34][35]. The smaller the difference, the smaller the cross-entropy.…”

Section: Multiscale Information Fusionmentioning

confidence: 99%

BLNN: Multiscale Feature Fusion‐Based Bilinear Fine‐Grained Convolutional Neural Network for Image Classification of Wood Knot Defects

et al. 2021

View full text Add to dashboard Cite

Wood defects are quickly identified from an optical image based on deep learning methodology, which effectively improves the wood utilization. The traditional neural network technique is unemployed for the wood defect detection of optical image used, which results from a long training time, low recognition accuracy, and nonautomatic extraction of defect image features. In this paper, a wood knot defect detection model (so-called BLNN) combined deep learning is reported. Two subnetworks composed of convolutional neural networks are trained by Pytorch. By using the feature extraction capabilities of the two subnetworks and combining the bilinear join operation, the fine-grained features of the image are obtained. The experimental results show that the accuracy has reached up 99.20%, and the training time is obviously reduced with the speed of defect detection about 0.0795 s/image. It indicates that BLNN has the ability to improve the accuracy of defect recognition and has a potential application in the detection of wood knot defects.

show abstract

Performance Analysis of Different Loss Function in Face Detection Architectures

Cited by 5 publications

References 22 publications

Deep Learning for Marine Science

Deep Learning for Marine Science

Toward efficient deep learning system for in-situ plankton image recognition

BLNN: Multiscale Feature Fusion‐Based Bilinear Fine‐Grained Convolutional Neural Network for Image Classification of Wood Knot Defects

Contact Info

Product

Resources

About