•We analysed over 320 COVID-19 images and 320 healthy control images.•We proposed an improved CNN to extract individual image-level features.•We proposed to use GCN to extract relation-aware ...representations.•We proposed a DFF technology to combine features from GCN and CNN.•The proposed FCGNet gives better performance than 15 state-of-the-art approaches.
(Aim) COVID-19 is an infectious disease spreading to the world this year. In this study, we plan to develop an artificial intelligence based tool to diagnose on chest CT images.
(Method) On one hand, we extract features from a self-created convolutional neural network (CNN) to learn individual image-level representations. The proposed CNN employed several new techniques such as rank-based average pooling and multiple-way data augmentation. On the other hand, relation-aware representations were learnt from graph convolutional network (GCN). Deep feature fusion (DFF) was developed in this work to fuse individual image-level features and relation-aware features from both GCN and CNN, respectively. The best model was named as FGCNet.
(Results) The experiment first chose the best model from eight proposed network models, and then compared it with 15 state-of-the-art approaches.
(Conclusion) The proposed FGCNet model is effective and gives better performance than all 15 state-of-the-art methods. Thus, our proposed FGCNet model can assist radiologists to rapidly detect COVID-19 from chest CT images.
This paper presents a novel multi-pooling architecture generated by combining the advantages of wavelet and max-pooling operations in convolutional neural networks (CNNs), focusing on semantic ...segmentation tasks. CNNs often use pooling to reduce the number of parameters, improve invariance to certain distortions, and enlarge the receptive field. However, pooling can cause information loss and thus is detrimental to further operations such as feature extraction and analysis. This problem is particularly critical for semantic segmentation, where each pixel of an image is assigned to a specific class to divide the image into disjoint regions of interest. To address this problem, pooling strategies based on wavelets-operations have been proposed with the promise to achieve a better trade-off between receptive field size and computational efficiency. Previous works have confirmed the superiority of wavelet pooling over the traditional one in semantic segmentation tasks. However, we have observed in our computational experiments that the expressive gains reported from the use of wavelet pooling in other segmentation tasks were not observed in the scope of aerial imagery due to imprecision in the segmentation of image details. The combination of wavelet pooling and max-pooling, a solution not yet reported in the literature, can address that issue. Such gap observed in the pooling area motivated the two proposals that are the main contributions of this paper: (a) A new multi-pooling strategy combining wavelet and traditional pooling in a new network structure suitable for aerial image segmentation tasks; (b) Two-stream architectures using the traditional max-pooling and wavelet pooling as streams. These proposals were implemented using the Segnet, a known architecture for semantic segmentation. The computational experiments, based on the IRRG images from the Potsdam and Vaihingen data sets, demonstrated that the proposed architectures surpassed the original Segnet architecture’s performance with results comparable to state-of-the-art approaches.
Display omitted
•A new multi-pooling strategy combining wavelet and traditional pooling.•A new version of Segnet, named MPSegnet, using the new multi-pooling strategy.•A two-stream architecture that combines the Segnet network with MPSegnet.•The multi-pooling scheme efficiency was verified using complexity and visual analysis.•Experiments showing that our methods are comparable to the state-of-the-art.
In the past decade, transportation network companies (TNCs) such as Uber, Lyft, and Via have established themselves as a viable transportation alternative to other modes. However, the popularity of ...these services has come with a fair share of criticism for their negative externalities such as increasing vehicle miles traveled and congestion in cities. Pooled ride-hailing trips, in which all or a part of two individual (or group) trips are combined in and served by a single vehicle, have the potential to reduce these externalities. Pooling of rides is an effective solution to reduce congestion and travel cost, but pooled rides still represent a small percentage of the total trips served (and miles driven) by TNCs relative to single-occupancy (and without customer) vehicle miles. Both TNCs and cities alike will benefit from understanding what factors encourage or deter pooling a ride-hailing trip. In this study, newly available Chicago transportation network provider data were explored to identify the extent to which different socioeconomic, spatiotemporal, and trip characteristics affect willingness to pool (WTP) in ride-hailing trips. Multivariate linear regression and machine-learning models were employed to understand and predict WTP based on location, time, and trip factors. The results show intuitive trends, with income level at drop-off and pickup locations and airport trips as the most important predictors of WTP. Results from this study can help TNCs and cities devise strategies that increase pooled ride-hailing, thereby reducing adverse transportation and energy impacts from ride-hailing modes.
We propose a deep bilinear model for blind image quality assessment that works for both synthetically and authentically distorted images. Our model constitutes two streams of deep convolutional ...neural networks (CNNs), specializing in two distortion scenarios separately. For synthetic distortions, we first pre-train a CNN to classify the distortion type and the level of an input image, whose ground truth label is readily available at a large scale. For authentic distortions, we make use of a pre-train CNN (VGG-16) for the image classification task. The two feature sets are bilinearly pooled into one representation for a final quality prediction. We fine-tune the whole network on the target databases using a variant of stochastic gradient descent. The extensive experimental results show that the proposed model achieves state-of-the-art performance on both synthetic and authentic IQA databases. Furthermore, we verify the generalizability of our method on the large-scale Waterloo Exploration Database, and demonstrate its competitiveness using the group maximum differentiation competition methodology.
The paper systematically studies the impact of a range of recent advances in convolution neural network (CNN) architectures and learning methods on the object categorization (ILSVRC) problem. The ...evaluation tests the influence of the following choices of the architecture: non-linearity (ReLU, ELU, maxout, compatability with batch normalization), pooling variants (stochastic, max, average, mixed), network width, classifier design (convolutional, fully-connected, SPP), image pre-processing, and of learning parameters: learning rate, batch size, cleanliness of the data, etc.
The performance gains of the proposed modifications are first tested individually and then in combination. The sum of individual gains is greater than the observed improvement when all modifications are introduced, but the “deficit” is small suggesting independence of their benefits.
We show that the use of 128 × 128 pixel images is sufficient to make qualitative conclusions about optimal network structure that hold for the full size Caffe and VGG nets. The results are obtained an order of magnitude faster than with the standard 224 pixel images.
Convolutional Neural Networks for Speech Recognition Abdel-Hamid, Ossama; Mohamed, Abdel-rahman; Hui Jiang ...
IEEE/ACM transactions on audio, speech, and language processing,
2014-Oct., 2014-10-00, 20141001, Volume:
22, Issue:
10
Journal Article
Peer reviewed
Open access
Recently, the hybrid deep neural network (DNN)-hidden Markov model (HMM) has been shown to significantly improve speech recognition performance over the conventional Gaussian mixture model (GMM)-HMM. ...The performance improvement is partially attributed to the ability of the DNN to model complex correlations in speech features. In this paper, we show that further error rate reduction can be obtained by using convolutional neural networks (CNNs). We first present a concise description of the basic CNN and explain how it can be used for speech recognition. We further propose a limited-weight-sharing scheme that can better model speech features. The special structure such as local connectivity, weight sharing, and pooling in CNNs exhibits some degree of invariance to small shifts of speech features along the frequency axis, which is important to deal with speaker and environment variations. Experimental results show that CNNs reduce the error rate by 6%-10% compared with DNNs on the TIMIT phone recognition and the voice search large vocabulary speech recognition tasks.
Automatic segmentation of polyps in endoscopic images is crucial for early diagnosis and surgical planning of colorectal cancer. However, polyps closely resemble surrounding mucosal tissue in both ...texture and indistinct borders and vary in size, appearance, and location which possess great challenge to polyp segmentation. Although some recent attempts have been made to apply Vision Transformer (ViT) to polyp segmentation and achieved promising performance, their application in clinical scenarios is still limited by high computational complexity, large model size, redundant dependencies, and significant training costs. To address these limitations, we propose a novel ViT-based approach named Polyp-LVT, strategically replacing the attention layer in the encoder with a global max pooling layer, which significantly reduces the model’s parameter count and computational cost while keeping the performance undegraded. Furthermore, we introduce a network block, named Inter-block Feature Fusion Module (IFFM), into the decoder, aiming to offer a streamlined yet highly efficient feature extraction. We conduct extensive experiments on three public polyp image benchmarks to evaluate our method. The experimental results show that compared with the baseline models, our Polyp-LVT network achieves a nearly 44% reduction in model parameters while gaining comparable segmentation performance.
Person re-identification aims to identify whether pairs of images belong to the same person or not. This problem is challenging due to large differences in camera views, lighting and background. One ...of the mainstream in learning CNN features is to design loss functions which reinforce both the class separation and intra-class compactness. In this paper, we propose a novel Orthogonal Center Learning method with Subspace Masking for person re-identification. We make the following contributions: 1) we develop a center learning module to learn the class centers by simultaneously reducing the intra-class differences and inter-class correlations by orthogonalization; 2) we introduce a subspace masking mechanism to enhance the generalization of the learned class centers; and 3) we propose to integrate the average pooling and max pooling in a regularizing manner that fully exploits their powers. Extensive experiments show that our proposed method consistently outperforms the state-of-the-art methods on large-scale ReID datasets including Market-1501, DukeMTMC-ReID, CUHK03 and MSMT17.
P2T: Pyramid Pooling Transformer for Scene Understanding Wu, Yu-Huan; Liu, Yun; Zhan, Xin ...
IEEE transactions on pattern analysis and machine intelligence,
2023-Nov.-1, 2023-11-1, 20231101, Volume:
45, Issue:
11
Journal Article
Peer reviewed
Recently, the vision transformer has achieved great success by pushing the state-of-the-art of various vision tasks. One of the most challenging problems in the vision transformer is that the large ...sequence length of image tokens leads to high computational cost (quadratic complexity). A popular solution to this problem is to use a single pooling operation to reduce the sequence length. This paper considers how to improve existing vision transformers, where the pooled feature extracted by a single pooling operation seems less powerful. To this end, we note that pyramid pooling has been demonstrated to be effective in various vision tasks owing to its powerful ability in context abstraction. However, pyramid pooling has not been explored in backbone network design. To bridge this gap, we propose to adapt pyramid pooling to Multi-Head Self-Attention (MHSA) in the vision transformer, simultaneously reducing the sequence length and capturing powerful contextual features. Plugged with our pooling-based MHSA, we build a universal vision transformer backbone, dubbed Pyramid Pooling Transformer (P2T). Extensive experiments demonstrate that, when applied P2T as the backbone network, it shows substantial superiority in various vision tasks such as image classification, semantic segmentation, object detection, and instance segmentation, compared to previous CNN- and transformer-based networks. The code will be released at https://github.com/yuhuan-wu/P2T .