This article compares two style transfer methods in imageprocessing: the traditional method, which synthesizes new images by stitching together small patches from existing pattern images, and a modern machine learnin...
详细信息
image segmentation constitutes a critical component within the realm of medical imageprocessing and analysis, bearing profound implications on treatment efficacy and patient survival rates. This technique serves as a...
详细信息
All In the realm of communication, individuals employ two primary modes: written and spoken language. Handwriting, in particular, serves as a powerful tool for conveying information and emotions across various context...
详细信息
In medical imageprocessing, categorizing brain tumors is one of the most critical and challenging challenges that must be solved. Because manual classification carried out with the assistance of humans often leads to...
详细信息
To address the issue of low accuracy and poor robustness of perceptual learning in complex scenarios, a new method integrating computer vision and machinelearning is adopted, that is, by applying deep neuralnetworks...
详细信息
In this paper, a semantic-based intangible cultural heritage database is constructed based on the integration of structured retrieval and the characteristics of C language, and then it is debugged and compiled, and th...
详细信息
While image data starts to enjoy the simple-but-effective self-supervised learning scheme built upon masking and self-reconstruction objective thanks to the introduction of tokenization procedure and vision transforme...
详细信息
ISBN:
(纸本)9798350318920;9798350318937
While image data starts to enjoy the simple-but-effective self-supervised learning scheme built upon masking and self-reconstruction objective thanks to the introduction of tokenization procedure and vision transformer backbone, convolutional neuralnetworks as another important and widely-adopted architecture for image data, though having contrastive-learning techniques to drive the self-supervised learning, still face the difficulty of leveraging such straight-forward and general masking operation to benefit their learning process significantly. In this work, we aim to alleviate the burden of including masking operation into the contrastive-learning framework for convolutional neuralnetworks as an extra augmentation method. In addition to the additive but unwanted edges (between masked and unmasked regions) as well as other adverse effects caused by the masking operations for ConvNets, which have been discussed by prior works, we particularly identify the potential problem where for one view in a contrastive sample-pair the randomly-sampled masking regions could be overly concentrated on important/salient objects thus resulting in misleading contrastiveness to the other view. To this end, we propose to explicitly take the saliency constraint into consideration in which the masked regions are more evenly distributed among the foreground and background for realizing the masking-based augmentation. Moreover, we introduce hard negative samples by masking larger regions of salient patches in an input image. Extensive experiments conducted on various datasets, contrastive learning mechanisms, and downstream tasks well verify the efficacy as well as the superior performance of our proposed method with respect to several state-of-the-art baselines. Our code is publicly available at: https://***/joycenerd/Saliency-Guided-Masking-for-ConvNets
The proceedings contain 158 papers. The topics discussed include: duct inspection and monitoring robot;deep learning-based approaches for preventing and predicting wild animals disappearance: a review;classification a...
ISBN:
(纸本)9798350394528
The proceedings contain 158 papers. The topics discussed include: duct inspection and monitoring robot;deep learning-based approaches for preventing and predicting wild animals disappearance: a review;classification and tracking of items on a moving conveyor belt using convolutional networks and imageprocessing;critical analysis of the 220/110/20 kV Sardanesti power substation from Romania in the context of identification elements of instability and insecurity;machinelearning based collaborative prediction of SSD failures in the cloud;the impact of explainable ai on low-accuracy models: a practical approach with movie genre prediction;utilizing transfer learning-based algorithms for breast ultrasound data in multi-instance classification;predictive maintenance model-based on multi-stage neural network systems for wind turbines;and using teaching learning-based optimization with convolutional neural network to detect pneumonia based on chest X-Ray images.
Deep learning techniques involving Generative Adversarial networks (GANs) enable artificially generated facial images. This alone presents difficulties in terms of authenticity resulting in ethical concerns among inst...
详细信息
machinelearning, particularly convolutional neuralnetworks (CNNs), has gained prominence in healthcare applications, including medical diagnosis and clinical support. However, the increasing size of CNNs poses chall...
详细信息
ISBN:
(纸本)9783031790379;9783031790386
machinelearning, particularly convolutional neuralnetworks (CNNs), has gained prominence in healthcare applications, including medical diagnosis and clinical support. However, the increasing size of CNNs poses challenges in resource-constrained medical devices and real-time applications. This paper explores the effectiveness of pruning and quantization on the ResNet50 model within the MedMNIST dataset, a valuable resource for medical image classification. The study evaluates a surrogate-based multiobjective compression method on three MedMNIST datasets: RetinaMNIST for diabetic retinopathy grading, DermaMNIST for disease categorization, and BloodMNIST for blood cell classification. Results demonstrate that the proposed compression method successfully identifies less computationally intensive models while maintaining or improving accuracy across all three healthcare-related datasets. A reduction of about 50% in inference time and an increase of more than 1% in accuracy were observed. These findings emphasize the practicality of compression techniques in healthcare applications, particularly for resource-constrained environments and real-time decision-making scenarios. This research opens avenues for further validation and exploration in other healthcare-related applications with higher-quality neural network models, ultimately enhancing the deployment of machinelearning in the healthcare domain.
暂无评论