Large scale classifiers for visual classification tasks

Image classification is a fundamental task in remote sensing image processing. In recent years, deep convolutional neural networks (DCNNs) have experienced significant breakthroughs in natural image recognition. The remote sensing field, however, is still lacking a large-scale benchmark similar to ImageNet. In this paper, we propose a remote sensing image classification benchmark (RSI-CB) based on massive, scalable, and diverse crowdsourced data. Using crowdsourced data, such as Open Street Map (OSM) data, ground objects in remote sensing images can be annotated effectively using points of interest, vector data from OSM, or other crowdsourced data. These annotated images can, then, be used in remote sensing image classification tasks. Based on this method, we construct a worldwide large-scale benchmark for remote sensing image classification. This benchmark has large-scale geographical distribution and large total image number. It contains six categories with 35 sub-classes of more than 24,000 images of size 256 × 256 pixels. This classification system of ground objects is defined according to the national standard of land-use classification in China and is inspired by the hierarchy mechanism of ImageNet. Finally, we conduct numerous experiments to compare RSI-CB with the SAT-4, SAT-6, and UC-Merced data sets. The experiments show that RSI-CB is more suitable as a benchmark for remote sensing image classification tasks than other benchmarks in the big data era and has many potential applications.

Download Full-text

Multiactivation Pooling Method in Convolutional Neural Networks for Image Recognition

Wireless Communications and Mobile Computing ◽

10.1155/2018/8196906 ◽

2018 ◽

Vol 2018 ◽

pp. 1-15 ◽

Cited By ~ 5

Author(s):

Qi Zhao ◽

Shuchang Lyu ◽

Boxue Zhang ◽

Wenquan Feng

Keyword(s):

Neural Networks ◽

Image Processing ◽

Big Data ◽

Convolutional Neural Networks ◽

Image Recognition ◽

Large Scale ◽

Fog Computing ◽

Feature Extractor ◽

Benchmark Datasets ◽

Classification Tasks

Convolutional neural networks (CNNs) are becoming more and more popular today. CNNs now have become a popular feature extractor applying to image processing, big data processing, fog computing, etc. CNNs usually consist of several basic units like convolutional unit, pooling unit, activation unit, and so on. In CNNs, conventional pooling methods refer to 2×2 max-pooling and average-pooling, which are applied after the convolutional or ReLU layers. In this paper, we propose a Multiactivation Pooling (MAP) Method to make the CNNs more accurate on classification tasks without increasing depth and trainable parameters. We add more convolutional layers before one pooling layer and expand the pooling region to 4×4, 8×8, 16×16, and even larger. When doing large-scale subsampling, we pick top-k activation, sum up them, and constrain them by a hyperparameter σ. We pick VGG, ALL-CNN, and DenseNets as our baseline models and evaluate our proposed MAP method on benchmark datasets: CIFAR-10, CIFAR-100, SVHN, and ImageNet. The classification results are competitive.

Download Full-text

Developmental dyslexics show altered allocation of attention in visual classification tasks

Acta Neurologica Scandinavica ◽

10.1034/j.1600-0404.2003.02060.x ◽

2003 ◽

Vol 107 (1) ◽

pp. 22-30 ◽

Cited By ~ 6

Author(s):

J. Russeler ◽

S. Johannes ◽

J. Kowalczuk ◽

B. M. Wieringa ◽

T. F. Munte

Keyword(s):

Visual Classification ◽

Classification Tasks

Download Full-text

Automatic Construction and Global Optimization of a Multisentiment Lexicon

Computational Intelligence and Neuroscience ◽

10.1155/2016/2093406 ◽

2016 ◽

Vol 2016 ◽

pp. 1-8 ◽

Cited By ~ 5

Author(s):

Xiaoping Yang ◽

Zhongxia Zhang ◽

Zhongqiu Zhang ◽

Yuting Mo ◽

Lianbei Li ◽

...

Keyword(s):

Global Optimization ◽

Large Scale ◽

Language Model ◽

Superior Performance ◽

Optimization Framework ◽

Test Intensity ◽

Sentiment Lexicon ◽

Classification Tasks ◽

Network Language ◽

Accurate Quantification

Manual annotation of sentiment lexicons costs too much labor and time, and it is also difficult to get accurate quantification of emotional intensity. Besides, the excessive emphasis on one specific field has greatly limited the applicability of domain sentiment lexicons (Wang et al., 2010). This paper implements statistical training for large-scale Chinese corpus through neural network language model and proposes an automatic method of constructing a multidimensional sentiment lexicon based on constraints of coordinate offset. In order to distinguish the sentiment polarities of those words which may express either positive or negative meanings in different contexts, we further present a sentiment disambiguation algorithm to increase the flexibility of our lexicon. Lastly, we present a global optimization framework that provides a unified way to combine several human-annotated resources for learning our 10-dimensional sentiment lexicon SentiRuc. Experiments show the superior performance of SentiRuc lexicon in category labeling test, intensity labeling test, and sentiment classification tasks. It is worth mentioning that, in intensity label test, SentiRuc outperforms the second place by 21 percent.

Download Full-text

Large scale visual classification with SVM, create the unique article through NLP

2017 Seventeenth International Conference on Advances in ICT for Emerging Regions (ICTer) ◽

10.1109/icter.2017.8257788 ◽

2017 ◽

Author(s):

M.A.N. Madushani

Keyword(s):

Large Scale ◽

Visual Classification

Download Full-text

Spatio–Temporal Image Representation of 3D Skeletal Movements for View-Invariant Action Recognition with Deep Convolutional Neural Networks

Sensors ◽

10.3390/s19081932 ◽

2019 ◽

Vol 19 (8) ◽

pp. 1932 ◽

Cited By ~ 4

Author(s):

Huy Hieu Pham ◽

Houssam Salmane ◽

Louahdi Khoudour ◽

Alain Crouzil ◽

Pablo Zegers ◽

...

Keyword(s):

Neural Networks ◽

Convolutional Neural Networks ◽

Action Recognition ◽

Large Scale ◽

Image Representation ◽

Human Action ◽

Computational Time ◽

Deep Convolutional Neural Networks ◽

Classification Tasks ◽

Spatio Temporal

Designing motion representations for 3D human action recognition from skeleton sequences is an important yet challenging task. An effective representation should be robust to noise, invariant to viewpoint changes and result in a good performance with low-computational demand. Two main challenges in this task include how to efficiently represent spatio–temporal patterns of skeletal movements and how to learn their discriminative features for classification tasks. This paper presents a novel skeleton-based representation and a deep learning framework for 3D action recognition using RGB-D sensors. We propose to build an action map called SPMF (Skeleton Posture-Motion Feature), which is a compact image representation built from skeleton poses and their motions. An Adaptive Histogram Equalization (AHE) algorithm is then applied on the SPMF to enhance their local patterns and form an enhanced action map, namely Enhanced-SPMF. For learning and classification tasks, we exploit Deep Convolutional Neural Networks based on the DenseNet architecture to learn directly an end-to-end mapping between input skeleton sequences and their action labels via the Enhanced-SPMFs. The proposed method is evaluated on four challenging benchmark datasets, including both individual actions, interactions, multiview and large-scale datasets. The experimental results demonstrate that the proposed method outperforms previous state-of-the-art approaches on all benchmark tasks, whilst requiring low computational time for training and inference.

Download Full-text