Many computes vision applications are computationally challenging especially when they need to meet real-time constraints. A major problem with special purpose systems is that they require the developers of image-proc...
详细信息
ISBN:
(纸本)0769509908
Many computes vision applications are computationally challenging especially when they need to meet real-time constraints. A major problem with special purpose systems is that they require the developers of image-processing applications to be aware of the low-level hardware design, making the task cumbersome. To avoid inflexible and expensive hardware designs, another possible alternative is a network of workstations (NOW) platform put together with off-the-shelf workstations and networking hardware. Still, one had to manually schedule an algorithm to the available processors of the NOW to make efficient use of the resources. However, this approach is time consuming and impractical for a vision system that must perform a variety of different algorithms, with new algorithms being constantly developed. Improved support for program development is absolutely necessary before the full benefits of parallel architectures can be realized for vision applications. Towards this goal, an automatic compile-time scheduler has been developed to schedule input tasks of vision applications with precedence constraints onto available processors. the scheduler exploits both spatial (parallelism) and temporal (pipelining) concurrency to make the best use of machine resources. Two important scheduling problems are addressed. First, given a task graph and a desired throughput, a schedule is constructed to achieve the desired throughput withthe minimum number of processors. Second, given a task graph and a finite set of available resources, a schedule is constructed such that the throughput is maximized while meeting the resource constraints. Results from simulations show that the scheduler and proposed optimization techniques effectively tackle these problems by maximizing the processor utilization. A code generator has been developed to generate parallel programs automatically. the execution profiles of the resulting parallel programs demonstrate the feasibility of the scheduler. the to
the scarcity of accurately labeled data critically hampers the usage of deep learning models. this issue is highlighted in areas (e.g., biological sciences) where data annotation results in an expert-demanding, labor-...
详细信息
ISBN:
(数字)9798350376036
ISBN:
(纸本)9798350376043
the scarcity of accurately labeled data critically hampers the usage of deep learning models. this issue is highlighted in areas (e.g., biological sciences) where data annotation results in an expert-demanding, labor-intensive and error-prone task. While state-of-the-art semi-supervised approaches have proven effective in circumventing this limitation, their reliance on pre-trained architectures and large validation sets to deliver effective solutions still poses a challenge. In this work we introduce an iterative contrastive-based meta-pseudo-Iabeling method for training non-pre-trained custom CNN architectures for image classification in conditions of limited labeled and abundant unlabeled data, with no dependency on a validation set. It generates multiple models across a few iterations, which are in turn exploited in an ensemble manner to label the unlabeled data and train a final classifier. Our approach starts by capitalizing on contrastive learning to enhance the representation ability of two collaborative networks while eliminating the need of pre-trained architectures. then, during each iteration, the networks are trained within a teacher-student based cross-training setup, where OPFSemi (teacher) propagates labels from labeled to unlabeled on the non-linear 2D latent space projections of each network's (student) deep features; afterward, the pseudo-labels withthe highest top 10% confidence, per class, are picked to fine-tune the other network in a cross-training manner, jointly mitigating confirmation bias and overfitting while improving the generalization ability of the networks as iterations evolve. Our method is evaluated on three challenging biological image datasets with only 5 % of labeled samples, demonstrating its effectiveness and robustness when compared to two direct baselines and six state-of-the-art methods from three different semi-supervised learning paradigms.
Oil palm is one of the potential tree crops in thailand. However, the production of oil palm has been experienced many aspects. Price factor is also one of the problems. Price of oil palm depends on the amount of oil ...
详细信息
ISBN:
(数字)9781665415545
ISBN:
(纸本)9781665446969
Oil palm is one of the potential tree crops in thailand. However, the production of oil palm has been experienced many aspects. Price factor is also one of the problems. Price of oil palm depends on the amount of oil content in the oil palm fruit which are estimated by an expert. the main consideration is the ripeness of the oil palm fresh fruit bunches. An expert determines using its surface color. A different experience of experts leads to a different estimation. the problem may be solved using the chemical analysis methods which more accurate. However, it takes time and uncomfortable. In this research, artificial intelligence (AI) will be applied to estimate the oil content in a fresh fruit bunch (FFB). Two popular types of oil palms in thailand are used in this work. the Nigrescene fruit, color varies from dark purple to red orange depending on its gene and ripeness. the Virescene fruit, color changes from green to orange. the surface color of an oil palm fruit and structure of the bunch were considered as the feature set. An oil palm FFB image from a smartphone camera was fed to the model for predicting the oil content in FFB. Several models such as multi linear regression, artificial neural network and convolution neural network will be observed. the measure of the quality's model uses the root mean square error (RMSE). the convolution neural network produces the average of RMSE at 727 for Nigrescene and at 4.83 for Virescene.
Virtual Humans (VHs) with high levels of anthropomorphism in visual appearance and behavior can enhance user experience in movies, games, and other interactive media. Users often seek human-like representations that i...
详细信息
ISBN:
(数字)9798350376036
ISBN:
(纸本)9798350376043
Virtual Humans (VHs) with high levels of anthropomorphism in visual appearance and behavior can enhance user experience in movies, games, and other interactive media. Users often seek human-like representations that include realistic movement, emotion, and gender, fostering a stronger sense of identification with VHs. Studies from Psychology have shown that people tend to evaluate characteristics of others within their own group differently, known as the in-group advantage. For example, women may be better at recognizing emotions in other women than in men. Researchers have also noted differences in feature recognition based on boththe gender of the person and the gender of the perceiver, a phenomenon that also extends to VHs. Understanding how humans perceive VHs is crucial for improving user experience and representation in virtual environments. Gender is a key anthropomorphic characteristic in VHs, essential for representativeness, human identification, and user comfort. Typically, VHs assigned a specific gender exhibit stereotyped features such as movements, clothing, hairstyles, and colors, designed to be easily recognized by users. Insights into gender representation in VHs can guide the industry in modeling and animating VHs to achieve the desired impact. this tutorial introduces a methodology for modeling gender in VHs, from genderless virtual babies to genderless virtual adults, focusing on visual and behavioral aspects. Participants will learn how to create genderless VHs, enhancing gender representation and making virtual environments more inclusive for a diverse audience.
暂无评论