Improving Object Tracking by Added Noise and Channel Attention

CNN-based trackers, especially those based on Siamese networks, have recently attracted considerable attention because of their relatively good performance and low computational cost. For many Siamese trackers, learning a generic object model from a large-scale dataset is still a challenging task. In the current study, we introduce input noise as regularization in the training data to improve generalization of the learned model. We propose an Input-Regularized Channel Attentional Siamese (IRCA-Siam) tracker which exhibits improved generalization compared to the current state-of-the-art trackers. In particular, we exploit offline learning by introducing additive noise for input data augmentation to mitigate the overfitting problem. We propose feature fusion from noisy and clean input channels which improves the target localization. Channel attention integrated with our framework helps finding more useful target features resulting in further performance improvement. Our proposed IRCA-Siam enhances the discrimination of the tracker/background and improves fault tolerance and generalization. An extensive experimental evaluation on six benchmark datasets including OTB2013, OTB2015, TC128, UAV123, VOT2016 and VOT2017 demonstrate superior performance of the proposed IRCA-Siam tracker compared to the 30 existing state-of-the-art trackers.

Download Full-text

CharTeC-Net: An Efficient and Lightweight Character-Based Convolutional Network for Text Classification

Journal of Electrical and Computer Engineering ◽

10.1155/2020/9701427 ◽

2020 ◽

Vol 2020 ◽

pp. 1-7 ◽

Cited By ~ 2

Author(s):

Aboubakar Nasser Samatin Njikam ◽

Huan Zhao

Keyword(s):

Text Classification ◽

Building Block ◽

Large Scale ◽

State Of The Art ◽

Building Blocks ◽

Training Data ◽

Superior Performance ◽

Classification Problems ◽

Computationally Efficient ◽

Convolutional Network

This paper introduces an extremely lightweight (with just over around two hundred thousand parameters) and computationally efficient CNN architecture, named CharTeC-Net (Character-based Text Classification Network), for character-based text classification problems. This new architecture is composed of four building blocks for feature extraction. Each of these building blocks, except the last one, uses 1 × 1 pointwise convolutional layers to add more nonlinearity to the network and to increase the dimensions within each building block. In addition, shortcut connections are used in each building block to facilitate the flow of gradients over the network, but more importantly to ensure that the original signal present in the training data is shared across each building block. Experiments on eight standard large-scale text classification and sentiment analysis datasets demonstrate CharTeC-Net’s superior performance over baseline methods and yields competitive accuracy compared with state-of-the-art methods, although CharTeC-Net has only between 181,427 and 225,323 parameters and weighs less than 1 megabyte.

Download Full-text

Attention-Aware Adversarial Network for Person Re-Identification

Applied Sciences ◽

10.3390/app9081550 ◽

2019 ◽

Vol 9 (8) ◽

pp. 1550 ◽

Cited By ~ 1

Author(s):

Aihong Shen ◽

Huasheng Wang ◽

Junjie Wang ◽

Hongchen Tan ◽

Xiuping Liu ◽

...

Keyword(s):

High Performance ◽

Large Scale ◽

Data Augmentation ◽

Fundamental Problem ◽

Training Data ◽

Specific Data ◽

Training Strategy ◽

Adversarial Network ◽

Benchmark Datasets ◽

Adversarial Training

Person re-identification (re-ID) is a fundamental problem in the field of computer vision. The performance of deep learning-based person re-ID models suffers from a lack of training data. In this work, we introduce a novel image-specific data augmentation method on the feature map level to enforce feature diversity in the network. Furthermore, an attention assignment mechanism is proposed to enforce that the person re-ID classifier focuses on nearly all important regions of the input person image. To achieve this, a three-stage framework is proposed. First, a baseline classification network is trained for person re-ID. Second, an attention assignment network is proposed based on the baseline network, in which the attention module learns to suppress the response of the current detected regions and re-assign attentions to other important locations. By this means, multiple important regions for classification are highlighted by the attention map. Finally, the attention map is integrated in the attention-aware adversarial network (AAA-Net), which generates high-performance classification results with an adversarial training strategy. We evaluate the proposed method on two large-scale benchmark datasets, including Market1501 and DukeMTMC-reID. Experimental results show that our algorithm performs favorably against the state-of-the-art methods.

Download Full-text

Multi-Margin based Decorrelation Learning for Heterogeneous Face Recognition

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2019/96 ◽

2019 ◽

Cited By ~ 2

Author(s):

Bing Cao ◽

Nannan Wang ◽

Xinbo Gao ◽

Jie Li ◽

Zhifeng Li

Keyword(s):

Face Recognition ◽

Large Scale ◽

State Of The Art ◽

Representation Learning ◽

Training Data ◽

Superior Performance ◽

Neural Network Approach ◽

Cross Domain ◽

Face Images ◽

Heterogeneous Face Recognition

Heterogeneous face recognition (HFR) refers to matching face images acquired from different domains with wide applications in security scenarios. However, HFR is still a challenging problem due to the significant cross-domain discrepancy and the lacking of sufficient training data in different domains. This paper presents a deep neural network approach namely Multi-Margin based Decorrelation Learning (MMDL) to extract decorrelation representations in a hyperspherical space for cross-domain face images. The proposed framework can be divided into two components: heterogeneous representation network and decorrelation representation learning. First, we employ a large scale of accessible visual face images to train heterogeneous representation network. The decorrelation layer projects the output of the first component into decorrelation latent subspace and obtain decorrelation representation. In addition, we design a multi-margin loss (MML), which consists of tetradmargin loss (TML) and heterogeneous angular margin loss (HAML), to constrain the proposed framework. Experimental results on two challenging heterogeneous face databases show that our approach achieves superior performance on both verification and recognition tasks, comparing with state-of-the-art methods.

Download Full-text

Accurate and Transferable Multitask Prediction of Chemical Properties with an Atoms-in-Molecule Neural Network

10.26434/chemrxiv.7151435.v2 ◽

2018 ◽

Author(s):

Roman Zubatyuk ◽

Justin S. Smith ◽

Jerzy Leszczynski ◽

Olexandr Isayev

Keyword(s):

Neural Network ◽

Molecular System ◽

Computational Cost ◽

Chemical Properties ◽

The State ◽

Molecular Properties ◽

Training Data ◽

Dft Methods ◽

Benchmark Datasets ◽

Quantum Phenomena

<p>Atomic and molecular properties could be evaluated from the fundamental Schrodinger’s equation and therefore represent different modalities of the same quantum phenomena. Here we present AIMNet, a modular and chemically inspired deep neural network potential. We used AIMNet with multitarget training to learn multiple modalities of the state of the atom in a molecular system. The resulting model shows on several benchmark datasets the state-of-the-art accuracy, comparable to the results of orders of magnitude more expensive DFT methods. It can simultaneously predict several atomic and molecular properties without an increase in computational cost. With AIMNet we show a new dimension of transferability: the ability to learn new targets utilizing multimodal information from previous training. The model can learn implicit solvation energy (like SMD) utilizing only a fraction of original training data, and archive MAD error of 1.1 kcal/mol compared to experimental solvation free energies in MNSol database.</p>

Download Full-text

An efficient pruning scheme of deep neural networks for Internet of Things applications

EURASIP Journal on Advances in Signal Processing ◽

10.1186/s13634-021-00744-4 ◽

2021 ◽

Vol 2021 (1) ◽

Author(s):

Chen Qi ◽

Shibo Shen ◽

Rongpeng Li ◽

Zhifeng Zhao ◽

Qing Liu ◽

...

Keyword(s):

Neural Network ◽

Neural Networks ◽

Internet Of Things ◽

Deep Neural Networks ◽

Computational Cost ◽

Superior Performance ◽

Compact Structure ◽

Resource Limited ◽

Benchmark Datasets ◽

Iot Devices

AbstractNowadays, deep neural networks (DNNs) have been rapidly deployed to realize a number of functionalities like sensing, imaging, classification, recognition, etc. However, the computational-intensive requirement of DNNs makes it difficult to be applicable for resource-limited Internet of Things (IoT) devices. In this paper, we propose a novel pruning-based paradigm that aims to reduce the computational cost of DNNs, by uncovering a more compact structure and learning the effective weights therein, on the basis of not compromising the expressive capability of DNNs. In particular, our algorithm can achieve efficient end-to-end training that transfers a redundant neural network to a compact one with a specifically targeted compression rate directly. We comprehensively evaluate our approach on various representative benchmark datasets and compared with typical advanced convolutional neural network (CNN) architectures. The experimental results verify the superior performance and robust effectiveness of our scheme. For example, when pruning VGG on CIFAR-10, our proposed scheme is able to significantly reduce its FLOPs (floating-point operations) and number of parameters with a proportion of 76.2% and 94.1%, respectively, while still maintaining a satisfactory accuracy. To sum up, our scheme could facilitate the integration of DNNs into the common machine-learning-based IoT framework and establish distributed training of neural networks in both cloud and edge.

Download Full-text

Gravity Control-Based Data Augmentation Technique for Improving VR User Activity Recognition

Symmetry ◽

10.3390/sym13050845 ◽

2021 ◽

Vol 13 (5) ◽

pp. 845

Author(s):

Dongheun Han ◽

Chulwoo Lee ◽

Hyeongyeop Kang

Keyword(s):

Activity Recognition ◽

Large Scale ◽

Data Augmentation ◽

Training Data ◽

Measurement Unit ◽

Gravitational Acceleration ◽

The Neural Network ◽

Typical Data ◽

Robust Recognition ◽

Gravity Acceleration

The neural-network-based human activity recognition (HAR) technique is being increasingly used for activity recognition in virtual reality (VR) users. The major issue of a such technique is the collection large-scale training datasets which are key for deriving a robust recognition model. However, collecting large-scale data is a costly and time-consuming process. Furthermore, increasing the number of activities to be classified will require a much larger number of training datasets. Since training the model with a sparse dataset can only provide limited features to recognition models, it can cause problems such as overfitting and suboptimal results. In this paper, we present a data augmentation technique named gravity control-based augmentation (GCDA) to alleviate the sparse data problem by generating new training data based on the existing data. The benefits of the symmetrical structure of the data are that it increased the number of data while preserving the properties of the data. The core concept of GCDA is two-fold: (1) decomposing the acceleration data obtained from the inertial measurement unit (IMU) into zero-gravity acceleration and gravitational acceleration, and augmenting them separately, and (2) exploiting gravity as a directional feature and controlling it to augment training datasets. Through the comparative evaluations, we validated that the application of GCDA to training datasets showed a larger improvement in classification accuracy (96.39%) compared to the typical data augmentation methods (92.29%) applied and those that did not apply the augmentation method (85.21%).

Download Full-text

Large-scale Semantic Parsing without Question-Answer Pairs

Transactions of the Association for Computational Linguistics ◽

10.1162/tacl_a_00190 ◽

2014 ◽

Vol 2 ◽

pp. 377-392 ◽

Cited By ~ 40

Author(s):

Siva Reddy ◽

Mirella Lapata ◽

Mark Steedman

Keyword(s):

Natural Language ◽

Large Scale ◽

Graph Matching ◽

State Of The Art ◽

The State ◽

Semantic Parsing ◽

Matching Problem ◽

Weak Supervision ◽

Benchmark Datasets

In this paper we introduce a novel semantic parsing approach to query Freebase in natural language without requiring manual annotations or question-answer pairs. Our key insight is to represent natural language via semantic graphs whose topology shares many commonalities with Freebase. Given this representation, we conceptualize semantic parsing as a graph matching problem. Our model converts sentences to semantic graphs using CCG and subsequently grounds them to Freebase guided by denotations as a form of weak supervision. Evaluation experiments on a subset of the Free917 and WebQuestions benchmark datasets show our semantic parser improves over the state of the art.

Download Full-text

Maximum Variance Hashing via Column Generation

Mathematical Problems in Engineering ◽

10.1155/2013/379718 ◽

2013 ◽

Vol 2013 ◽

pp. 1-10

Author(s):

Lei Luo ◽

Chao Zhang ◽

Yongrui Qin ◽

Chunyuan Zhang

Keyword(s):

Column Generation ◽

Large Scale ◽

Web Search ◽

Nearest Neighbor ◽

Computational Cost ◽

Multimedia Retrieval ◽

Training Data ◽

Nonlinear Dimensionality Reduction ◽

Maximum Variance ◽

Data Volume

With the explosive growth of the data volume in modern applications such as web search and multimedia retrieval, hashing is becoming increasingly important for efficient nearest neighbor (similar item) search. Recently, a number of data-dependent methods have been developed, reflecting the great potential of learning for hashing. Inspired by the classic nonlinear dimensionality reduction algorithm—maximum variance unfolding, we propose a novel unsupervised hashing method, named maximum variance hashing, in this work. The idea is to maximize the total variance of the hash codes while preserving the local structure of the training data. To solve the derived optimization problem, we propose a column generation algorithm, which directly learns the binary-valued hash functions. We then extend it using anchor graphs to reduce the computational cost. Experiments on large-scale image datasets demonstrate that the proposed method outperforms state-of-the-art hashing methods in many cases.

Download Full-text

Multiscale Semantic Feature Optimization and Fusion Network for Building Extraction Using High-Resolution Aerial Images and LiDAR Data

Remote Sensing ◽

10.3390/rs13132473 ◽

2021 ◽

Vol 13 (13) ◽

pp. 2473

Author(s):

Qinglie Yuan ◽

Helmi Zulhaidi Mohd Shafri ◽

Aidi Hizami Alias ◽

Shaiful Jahari Hashim

Keyword(s):

High Resolution ◽

Large Scale ◽

Spatial Information ◽

Feature Fusion ◽

Aerial Images ◽

Semantic Gap ◽

Superior Performance ◽

Lidar Data ◽

Building Extraction ◽

Hierarchical Features

Automatic building extraction has been applied in many domains. It is also a challenging problem because of the complex scenes and multiscale. Deep learning algorithms, especially fully convolutional neural networks (FCNs), have shown robust feature extraction ability than traditional remote sensing data processing methods. However, hierarchical features from encoders with a fixed receptive field perform weak ability to obtain global semantic information. Local features in multiscale subregions cannot construct contextual interdependence and correlation, especially for large-scale building areas, which probably causes fragmentary extraction results due to intra-class feature variability. In addition, low-level features have accurate and fine-grained spatial information for tiny building structures but lack refinement and selection, and the semantic gap of across-level features is not conducive to feature fusion. To address the above problems, this paper proposes an FCN framework based on the residual network and provides the training pattern for multi-modal data combining the advantage of high-resolution aerial images and LiDAR data for building extraction. Two novel modules have been proposed for the optimization and integration of multiscale and across-level features. In particular, a multiscale context optimization module is designed to adaptively generate the feature representations for different subregions and effectively aggregate global context. A semantic guided spatial attention mechanism is introduced to refine shallow features and alleviate the semantic gap. Finally, hierarchical features are fused via the feature pyramid network. Compared with other state-of-the-art methods, experimental results demonstrate superior performance with 93.19 IoU, 97.56 OA on WHU datasets and 94.72 IoU, 97.84 OA on the Boston dataset, which shows that the proposed network can improve accuracy and achieve better performance for building extraction.

Download Full-text

Multiple Saliency and Channel Sensitivity Network for Aggregated Convolutional Feature

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.33019013 ◽

2019 ◽

Vol 33 ◽

pp. 9013-9020

Author(s):

Xuanlu Xiang ◽

Zhipeng Wang ◽

Zhicheng Zhao ◽

Fei Su

Keyword(s):

State Of The Art ◽

Image Representation ◽

Training Data ◽

Gram Matrix ◽

Redundant Information ◽

Deep Architecture ◽

Benchmark Datasets ◽

Supervised Methods ◽

Ranking Loss ◽

Effective Channel

In this paper, aiming at two key problems of instance-level image retrieval, i.e., the distinctiveness of image representation and the generalization ability of the model, we propose a novel deep architecture - Multiple Saliency and Channel Sensitivity Network(MSCNet). Specifically, to obtain distinctive global descriptors, an attention-based multiple saliency learning is first presented to highlight important details of the image, and then a simple but effective channel sensitivity module based on Gram matrix is designed to boost the channel discrimination and suppress redundant information. Additionally, in contrast to most existing feature aggregation methods, employing pre-trained deep networks, MSCNet can be trained in two modes: the first one is an unsupervised manner with an instance loss, and another is a supervised manner, which combines classification and ranking loss and only relies on very limited training data. Experimental results on several public benchmark datasets, i.e., Oxford buildings, Paris buildings and Holidays, indicate that the proposed MSCNet outperforms the state-of-the-art unsupervised and supervised methods.

Download Full-text