Learning Sparse Features in Convolutional Neural Networks for Image Classification

In this work, we present an approach based on multilevel local as well as global Convolutional Neural Network (CNN) feature matching to retrieve near duplicate images. CNN features are suitable for visual matching. The CNN features of entire image may not give accuracy in retrieval due to various image editing/capturing operations. Our retrieval task focuses on matching image pairs based on local and global levels. In local matching, an image is segmented into fixed size blocks followed by extracting patches by considering neighboring regions at different levels. Matching local image patches at different levels provides robustness to our retrieval model. In local patch extraction, we select blocks containing SURF feature points instead of selecting all blocks. CNN features are extracted and stored for each image patch and then followed by extraction of global CNN features. Finally, similarity between image pairs is computed by considering all extracted CNN features. Our similarity function is based on correlation and number of blocks found in matching. We implemented our proposed approach on benchmarking Holiday dataset. Retrieval results show remarkable improvement in mean average precision (mAP) on the dataset.

In response to the extensive and complex public comment data within the government system, this article presents an emotion analysis model for government information based on a dual attention multi-layer convolutional neural network (DA-MLCNN). This model exhibits enhanced generalization and higher accuracy, addressing limitations in expression, difficulty with correlation, and low classification accuracy in sentiment analysis of government media public comments. The model processes public comments by training a convolutional neural network, extracting features at each fully connected layer, and sequentially feeding these features into the classifier for comparison. Selecting the low-level fully connected layer activated by the Rectified Linear Unit (ReLU) function as the feature extraction layer yields a higher recognition rate than using the high-level fully connected layer. This study selects the ReLU layer of the AlexNet convolutional neural network model as the feature selection layer and optimizes the training data and classifier construction system. Experimental results demonstrate that the DA-MLCNN visual emotion analysis model achieves higher discrimination accuracy and better alignment with the emotions expressed in online media. The ablation experiment revealed that the classification accuracy of the DA-MLCNN model significantly surpasses that of the basic network VGGNet-16, proving that multi-layer convolutional neural network (CNN) feature fusion fully leverages the complementary advantages of different feature levels, thereby enhancing the effectiveness of sentiment classification

We propose simple and effective models for the image annotation that make use of Convolutional Neural Network (CNN) features extracted from an image and word embedding vectors to represent their associated tags. Our first set of models is based on the Canonical Correlation Analysis (CCA) framework that helps in modeling both views - visual features (CNN feature) and textual features (word embedding vectors) of the data. Results on all three variants of the CCA models, namely linear CCA, kernel CCA and CCA with k-nearest neighbor (CCA-KNN) clustering, are reported. The best results are obtained using CCA-KNN which outperforms previous results on the Corel-5k and the ESP-Game datasets and achieves comparable results on the IAPRTC-12 dataset. In our experiments we evaluate CNN features in the existing models which bring out the advantages of it over dozens of handcrafted features. We also demonstrate that word embedding vectors perform better than binary vectors as a representation of the tags associated with an image. In addition we compare the CCA model to a simple CNN based linear regression model, which allows the CNN layers to be trained using back-propagation.

Automatic target recognition has been one of the hottest research in synthetic aperture radar (SAR) data processing. Noticing that popular recognition methods cannot utilize multiple features of SAR complex data, a method fused scattering center feature and deep convolutional neural network (CNN) feature is proposed in this letter. This method contains three key parts, namely, scattering center extraction and reconstruction block, CNN feature extraction block, and final feature fusion and classification block. In this process, the scattering center feature and CNN feature are fused at the level of feature maps, which retain the space information of 2-D feature maps. What is more, the proposed half end-to-end strategy realizes the automatic update of weighting parameters in feature extraction network and subnetwork, which promotes a better recognition efficiency. Experimental results on measured SAR data show that the proposed method can achieve better accuracy than other single feature-based methods and feature fusion methods.

Disaster damage detection through synergistic use of deep learning and 3D point cloud features derived from very high resolution oblique aerial images, and multiple-kernel-learning

Deep learning has achieved great success in the field of computer vision, and the precision in image classification and image detection has surpassed humans. Therefore, this paper combines deep learning and medical image segmentation, focusing on how to improve the accuracy and speed of segmentation algorithm of medical exercise rehabilitation image. Aiming at the shortcomings of traditional medical image recognition methods, a medical exercise rehabilitation image segmentation algorithm based on hierarchical features of convolutional neural networks is proposed, this paper calls it as hierarchical features of convolutional neural networks (HFCNN). The algorithm firstly samples the convolution output of multiple layers in the convolutional neural network to a unified scale and combines them to construct a hierarchical feature. This hierarchical feature combines the structural information of objects contained in the shallow layer of the network with the semantic information of objects contained in the deep layers of the network, so it has a strong ability to express. Secondly, the image can be segmented into multiple super pixels by the super pixel segmentation algorithm. The classifier is trained using the hierarchical features of the super pixel, and then the classification result is mapped back to the pixel. Finally, a fully connected conditional random field algorithm including one-potential potential energy and paired potential energy is constructed. The corresponding energy function is used to smooth the classification result of the pixel, and the regional consistency and continuity of the pixel mark are improved. Compared with many classical convolutional neural network algorithms, this algorithm not only accelerates the network convergence speed, shortens the training time, but also significantly improves the accuracy of segmentation algorithm of medical exercise rehabilitation image, showing good practical value.

Activation functions facilitate deep neural networks by introducing non-linearity to the learning process. The non-linearity feature gives the neural network the ability to learn complex patterns. Recently, the most widely used activation function is the Rectified Linear Unit (ReLU). Though, other various existing activation including hand-designed alternatives to ReLU have been proposed. However, none has succeeded in replacing ReLU due to their existing inconsistencies. In this work, activation function called ReLUMemristor-like Activation Function (RMAF) is proposed to leverage benefits of negative values in neural networks. RMAF introduces a constant parameter (α) and a threshold parameter (p) making the function smooth, non-monotonous, and introduces non-linearity in the network. Our experiments show that, the RMAF works better than ReLU and other activation functions on deeper models and across number of challenging datasets. Firstly, experiments are performed by training and classifying on multi-layer perceptron (MLP) over benchmark data such as the Wisconsin breast cancer, MNIST, Iris and Car evaluation. RMAF achieves high performance of 98.74%, 99.67%, 98.81% and 99.42% respectively, compared to Sigmoid, Tanh and ReLU. Secondly, experiments were performed on convolution neural network (ResNet) over MNIST, CIFAR-10 and CIFAR-100 data and observed the proposed activation function achieves higher performance accuracy of 99.73%, 98.77% and 79.82% respectively than Tanh, ReLU and Swish. Additionally, we experimented our work on deep networks i.e. squeeze network (SqueezeNet), Dense connected neural network (DenseNet121) and ImageNet dataset, which RMAF produced the best performance. We note that, the RMAF converges faster than the other functions and can replace ReLU in any neural network due to the efficiency, scalability and its similarity to both ReLU and Swish.

Robust RGB-D tracking via compact CNN features

Co-trained convolutional neural networks for automated detection of prostate cancer in multi-parametric MRI.

This paper proposes an efficient and robust Loop closure detection (LCD) method based on Convolutional neural network (CNN) feature. The primary method is called SeqCNNSLAM, in which both the outputs of the intermediate layer of a pre-trained CNN and the outputs of traditional sequence-based matching procedure are incorporated, making it possible to handle the viewpoint and condition variance properly. An acceleration algorithm for SeqCNNSLAM is developed to reduce the search range for the current image, resulting in a new LCD method called A-SeqCNNSLAM. To improve the applicability of A-SeqCNNSLAM to new environments, O-SeqCNNSLAM is proposed for online parameters adjustment in A-SeqCNNSLAM. In addition to the above work, we further put forward a promising idea to enhance SeqSLAM by integrating the both CNN features and VLAD's advantages called patch based SeqCNNSLAM (P-SeqCNNSLAM), and provide some preliminary experimental results to reveal its performance.

Convolution Neural Network (CNN) features have been widely used in visual tracking due to their powerful representation. As an important component of CNN, the pooling layer plays a critical role, but the max/average/min operation only explores the first-order information, which limits the discrimination ability of the CNN features in some complex situations. In this paper, a high-order pooling layer is integrated into the VGG16 network for visual tracking. In detail, a high-order covariance pooling layer is employed to replace the last maxpooling layer to learn discrimination features and is trained on the ImageNet and CUB200-2011 data sets. In tracking stage, the multiple levels of feature maps are extracted as the appearance representation of the target. After that, the extracted CNN features are integrated into the correlation filters framework when tracking is on-the-fly. The experimental results show that the proposed algorithm achieves excellent performance in both success rate and tracking accuracy.

The convolutional neural networks (CNN), including AlexNet, GoogleNet, VGGNet, etc. extract features for many computer vision problems which are very discriminative. The trained CNN model over one dataset performs reasonably well whereas on another dataset of similar type the hand-designed feature descriptor outperforms the same trained CNN model. The Rectified Linear Unit (ReLU) layer discards some values in order to introduce the non-linearity. In this paper, it is proposed that the discriminative ability of deep image representation using trained model can be improved by Average Biased ReLU (AB-ReLU) at the last few layers. Basically, AB-ReLU improves the discriminative ability in two ways: 1) it exploits some of the discriminative and discarded negative information of ReLU and 2) it also neglects the irrelevant and positive information used in ReLU. The VGGFace model trained in MatConvNet over the VGG-Face dataset is used as the feature descriptor for face retrieval over other face datasets. The proposed approach is tested over six challenging, unconstrained and robust face datasets (PubFig, LFW, PaSC, AR, FERET and ExtYale) and also on a large scale face dataset (PolyUNIR) in retrieval framework. It is observed that the AB-ReLU outperforms the ReLU when used with a pre-trained VGGFace model over the face datasets. The validation error by training the network after replacing all ReLUs with AB-ReLUs is also observed to be favorable over each dataset. The AB-ReLU even outperforms the state-of-the-art activation functions, such as Sigmoid, ReLU, Leaky ReLU and Flexible ReLU over all seven face datasets.

Face verification for on line application is a difficult problem and many researchers have tried to solve it by convolutional neural network. Among of them, most works used the last-hidden layer as the feature of face, and abandoned the features in the lower layers which indicate local information. To remedy this, we extract features of all layers in the convolutional neural network, and fuse these features together after dimensionality reduction with PCA. Then these features are utilized for face verification with neural network classifier. Experiment results show that complete features can improve the verification rate effectively than using the last-hidden layer only.

Recent works about convolutional neural networks (CNN) show breakthrough performance on various tasks. However, most of them only use the features extracted from the topmost layer of CNN instead of leveraging the features extracted from different layers. As the first group which explicitly addresses utilizing the features from different layers of CNN, we propose cross-layer CNN features which consist of the features extracted from multiple layers of CNN. Our experimental results show that our proposed cross-layer CNN features outperform not only the state-of-the-art results but also the features commonly used in the traditional CNN framework on three tasks — artistic style, artist, and architectural style classification. As shown by the experimental results, our proposed cross-layer CNN features achieve the best known performance on the three tasks in different domains, which makes our proposed cross-layer CNN features promising solutions for generic tasks.

Perceptual metrics based on features of deep Convolutional Neural Networks (CNNs) have shown remarkable success when used as loss functions in a range of computer vision problems and significantly outperform classical losses such as L1 or L2 in pixel space. The source of this success remains somewhat mysterious, especially since a good loss does not require a particular CNN architecture nor a particular training method. In this paper we show that similar success can be achieved even with losses based on features of a deep CNN with random filters. We use the tool of infinite CNNs to derive an analytical form for perceptual similarity in such CNNs, and prove that the perceptual distance between two images is equivalent to the maximum mean discrepancy (MMD) distance between local distributions of small patches in the two images. We use this equivalence to propose a simple metric for comparing two images which directly computes the MMD between local distributions of patches in the two images. Our proposed metric is simple to understand, requires no deep networks, and gives comparable performance to perceptual metrics in a range of computer vision tasks.