Sort by: Year Popularity Relevance

Multi-class Gaussian Process Classification with Noisy Inputs

, , ,  - 2020

It is a common practice in the supervised machine learning community to assume that the observed data are noise-free in the input attributes. Nevertheless, scenarios with input noise are common in real problems, as measurements are never perfectly accurate. If this input noise is not taken into account, a supervised machine learning method is exp...


A context based deep learning approach for unbalanced medical image segmentation

, , , , ,  - 2020

Automated medical image segmentation is an important step in many medical procedures. Recently, deep learning networks have been widely used for various medical image segmentation tasks, with U-Net and generative adversarial nets (GANs) being some of the commonly used ones. Foreground-background class imbalance is a common occurrence in medical i...


Video Saliency Prediction Using Enhanced Spatiotemporal Alignment Network

, , , ,  - 2020

Due to a variety of motions across different frames, it is highly challenging to learn an effective spatiotemporal representation for accurate video saliency prediction (VSP). To address this issue, we develop an effective spatiotemporal feature alignment network tailored to VSP, mainly including two key sub-networks: a multi-scale deformable con...


S$^{2}$OMGAN: Shortcut from Remote Sensing Images to Online Maps

, , , , , ,  - 2020

Traditional online maps, widely used on Internet such as Google map and Baidu map, are rendered from vector data. Timely updating online maps from vector data, of which the generating is time-consuming, is a difficult mission. It is a shortcut to generate online maps in time from remote sensing images, which can be acquired timely without vector ...


Towards High Performance Human Keypoint Detection

, ,  - 2020

Human keypoint detection from a single image is very challenging due to occlusion, blur, illumination and scale variance. In this paper, we address this problem from three aspects by devising an efficient network structure, proposing three effective training strategies, and exploiting four useful postprocessing techniques. First, we find that con...


OPFython: A Python-Inspired Optimum-Path Forest Classifier

, ,  - 2020

Machine learning techniques have been paramount throughout the last years, being applied in a wide range of tasks, such as classification, object recognition, person identification, image segmentation, among others. Nevertheless, conventional classification algorithms, e.g., Logistic Regression, Decision Trees, Bayesian classifiers, might lack co...


f-BRS: Rethinking Backpropagating Refinement for Interactive Segmentation

, , ,  - 2020

Deep neural networks have become a mainstream approach to interactive segmentation. As we show in our experiments, while for some images a trained network provides accurate segmentation result with just a few clicks, for some unknown objects it cannot achieve satisfactory result even with a large amount of user input. Recently proposed backpropag...


Symmetrical Synthesis for Deep Metric Learning

,  - 2020

Deep metric learning aims to learn embeddings that contain semantic similarity information among data points. To learn better embeddings, methods to generate synthetic hard samples have been proposed. Existing methods of synthetic hard sample generation are adopting autoencoders or generative adversarial networks, but this leads to more hyper-par...


Get Rid of Suspended Animation Problem: Deep Diffusive Neural Network on Graph Semi-Supervised Classification

 - 2020

Existing graph neural networks may suffer from the "suspended animation problem" when the model architecture goes deep. Meanwhile, for some graph learning scenarios, e.g., nodes with text/image attributes or graphs with long-distance node correlations, deep graph neural networks will be necessary for effective graph representation learning. In th...


The Synthinel-1 dataset: a collection of high resolution synthetic overhead imagery for building segmentation

, , ,  - 2020

Recently deep learning - namely convolutional neural networks (CNNs) - have yielded impressive performance for the task of building segmentation on large overhead (e.g., satellite) imagery benchmarks. However, these benchmark datasets only capture a small fraction of the variability present in real-world overhead imagery, limiting the ability to ...