Seam Carving is a content-aware image resizing method capable of modifying the width or height of pictures. Such an algorithm applies an energy function to evaluate the importance of each pixel in the image. In exceptional cases, such as images that contain people, the method frequently presents deformation of objects due to the energy function not being able to detect a person. In this context, this paper presents a modification of the energy function used in seam carving by employing a neural network which can detect human skin patterns. Such a modification aims at better-preserving people in images. The experiments show that the proposed method achieves superior performance in terms of visual quality through qualitative indexes compared to the original algorithm.
A máquina de aprendizagem mínima (MLM) é um método de aprendizado supervisionado que consiste na utilização de um mapeamento linear entre distâncias dos espaços de entrada e saída, seguido de um processo de otimização para, a partir das distâncias estimadas, estimar a saída. A etapa de teste da MLM envolve a resolução de um problema de otimização não-convexo, e pode sofrer com problemas associados a mínimos locais. Com isso em vista, neste artigo e apresentada uma formulação nessa etapa utilizando programação linear. Os experimentos mostram que o método proposto atinge desempenho semelhante aquele obtido com o algoritmo original, adicionalmente produzindo resultados com menor variância.
O Seam Carving é um método de redimensionamento capaz de modificar a largura ou altura de imagens sendo sensível ao seu conteúdo, esse algoritmo aplica uma função de energia para avaliar a importância de cada pixel. Em casos particulares, como imagens que contém pessoas, o método apresenta frequente deformação de objetos, devido a função de energia não ser apta a detecção de pessoa. Com isso em vista, este artigo apresenta uma formulação na função de energia para o Seam Carving específica para a preservação de pessoas nas imagens. Esta função de energia é elaborada a partir de uma rede neural que tem como argumentos de entrada a cor da pele para classificar o pixel em pele ou não pele.
Graph neural networks (GNNs) have become the de facto approach for supervised learning on graph data.To train these networks, most practitioners employ the categorical cross-entropy (CE) loss. We can attribute this largely to the probabilistic interpretability of models trained using CE, since it corresponds to the negative log of the categorical/softmax likelihood.We can attribute this largely to the probabilistic interpretation of CE, since it corresponds to the negative log of the categorical/softmax likelihood.Nonetheless, recent works have shown that deep learning models can benefit from adopting other loss functions. For instance, neural networks trained with symmetric losses (e.g., mean absolute error) are robust to label noise. Nonetheless, loss functions are a modeling choice and other training criteria can be employed — e.g., hinge loss and mean absolute error (MAE). Perhaps surprisingly, the effect of using different losses on GNNs has not been explored. In this preliminary work, we gauge the impact of different loss functions to the performance of GNNs for node classification under i) noisy labels and ii) different sample sizes. In contrast to findings on Euclidean domains, our results for GNNs show that there is no significant difference between models trained with CE and other classical loss functions on both aforementioned scenarios.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.