scholarly journals Cross Domain Adaptation of Crowd Counting with Model-Agnostic Meta-Learning

2021 ◽  
Vol 11 (24) ◽  
pp. 12037
Author(s):  
Xiaoyu Hou ◽  
Jihui Xu ◽  
Jinming Wu ◽  
Huaiyu Xu
Keyword(s):  
Feature Extraction ◽  
Supervised Learning ◽  
Density Estimation ◽  
Real World ◽  
Domain Adaptation ◽  
Manual Annotation ◽  
Crowd Counting ◽  
Cross Domain ◽  
Meta Learning ◽  
Density Map

Counting people in crowd scenarios is extensively conducted in drone inspections, video surveillance, and public safety applications. Today, crowd count algorithms with supervised learning have improved significantly, but with a reliance on a large amount of manual annotation. However, in real world scenarios, different photo angles, exposures, location heights, complex backgrounds, and limited annotation data lead to supervised learning methods not working satisfactorily, plus many of them suffer from overfitting problems. To address the above issues, we focus on training synthetic crowd data and investigate how to transfer information to real-world datasets while reducing the need for manual annotation. CNN-based crowd-counting algorithms usually consist of feature extraction, density estimation, and count regression. To improve the domain adaptation in feature extraction, we propose an adaptive domain-invariant feature extracting module. Meanwhile, after taking inspiration from recent innovative meta-learning, we present a dynamic-β MAML algorithm to generate a density map in unseen novel scenes and render the density estimation model more universal. Finally, we use a counting map refiner to optimize the coarse density map transformation into a fine density map and then regress the crowd number. Extensive experiments show that our proposed domain adaptation- and model-generalization methods can effectively suppress domain gaps and produce elaborate density maps in cross-domain crowd-counting scenarios. We demonstrate that the proposals in our paper outperform current state-of-the-art techniques.

scholarly journals Semi-Supervised learning with Collaborative Bagged Multi-label K-Nearest-Neighbors

2019 ◽  
Vol 9 (1) ◽  
pp. 226-242
Author(s):  
Nesma Settouti ◽  
Khalida Douibi ◽  
Mohammed El Amine Bechar ◽  
Mostafa El Habib Daho ◽  
Meryem Saidi
Keyword(s):  
Supervised Learning ◽  
Real World ◽  
Nearest Neighbors ◽  
Unlabeled Data ◽  
Manual Annotation ◽  
K Nearest Neighbors ◽  
Significant Attention

AbstractOver the last few years, Multi-label classification has received significant attention from researchers to solve many issues in many fields. The manual annotation of available datasets is time-consuming and need a huge effort from the expert, especially for Multi-label applications in which each example of learning is associated with many labels at once. To overcome the manual annotation drawback, and to take advantages from the large amounts of unlabeled data, many semi-supervised approaches were proposed in the literature to give more sophisticated and fast solutions to support the automatic labeling of the unlabeled data. In this paper, a Collaborative Bagged Multi-label K-Nearest-Neighbors (CobMLKNN) algorithm is proposed, that extend the co-Training paradigm by a Multi-label K-Nearest-Neighbors algorithm. Experiments on ten real-world Multi-label datasets show the effectiveness of CobMLKNN algorithm to improve the performance of MLKNN to learn from a small number of labeled samples by exploiting unlabeled samples.

Similarity-based meta-learning network with adversarial domain adaptation for cross-domain fault identification

2021 ◽  
Vol 217 ◽  
pp. 106829
Author(s):  
Yong Feng ◽  
Jinglong Chen ◽  
Zhuozheng Yang ◽  
Xiaogang Song ◽  
Yuanhong Chang ◽  
...  
Keyword(s):  
Domain Adaptation ◽  
Fault Identification ◽  
Learning Network ◽  
Cross Domain ◽  
Meta Learning

scholarly journals Tracklet Self-Supervised Learning for Unsupervised Person Re-Identification

2020 ◽  
Vol 34 (07) ◽  
pp. 12362-12369 ◽  
Author(s):  
Guile Wu ◽  
Xiatian Zhu ◽  
Shaogang Gong
Keyword(s):  
Unsupervised Learning ◽  
Supervised Learning ◽  
Large Scale ◽  
Domain Adaptation ◽  
Cluster Structure ◽  
Alternative Methods ◽  
Image Clustering ◽  
Clustering Methods ◽  
Data Annotation ◽  
Cross Domain

Existing unsupervised person re-identification (re-id) methods mainly focus on cross-domain adaptation or one-shot learning. Although they are more scalable than the supervised learning counterparts, relying on a relevant labelled source domain or one labelled tracklet per person initialisation still restricts their scalability in real-world deployments. To alleviate these problems, some recent studies develop unsupervised tracklet association and bottom-up image clustering methods, but they still rely on explicit camera annotation or merely utilise suboptimal global clustering. In this work, we formulate a novel tracklet self-supervised learning (TSSL) method, which is capable of capitalising directly from abundant unlabelled tracklet data, to optimise a feature embedding space for both video and image unsupervised re-id. This is achieved by designing a comprehensive unsupervised learning objective that accounts for tracklet frame coherence, tracklet neighbourhood compactness, and tracklet cluster structure in a unified formulation. As a pure unsupervised learning re-id model, TSSL is end-to-end trainable at the absence of source data annotation, person identity labels, and camera prior knowledge. Extensive experiments demonstrate the superiority of TSSL over a wide variety of the state-of-the-art alternative methods on four large-scale person re-id benchmarks, including Market-1501, DukeMTMC-ReID, MARS and DukeMTMC-VideoReID.

scholarly journals Crowd Counting using Deep Recurrent Spatial-Aware Network

2018 ◽  
Author(s):  
Lingbo Liu ◽  
Hongjun Wang ◽  
Guanbin Li ◽  
Wanli Ouyang ◽  
Liang Lin
Keyword(s):  
Neural Network ◽  
Real World ◽  
Local Refinement ◽  
Crowd Counting ◽  
Multi Scale ◽  
Residual Learning ◽  
Crowd Density ◽  
Real World Applications ◽  
Refinement Process ◽  
Density Map

Crowd counting from unconstrained scene images is a crucial task in many real-world applications like urban surveillance and management, but it is greatly challenged by the camera’s perspective that causes huge appearance variations in people’s scales and rotations. Conventional methods address such challenges by resorting to fixed multi-scale architectures that are often unable to cover the largely varied scales while ignoring the rotation variations. In this paper, we propose a unified neural network framework, named Deep Recurrent Spatial-Aware Network, which adaptively addresses the two issues in a learnable spatial transform module with a region-wise refinement process. Specifically, our framework incorporates a Recurrent Spatial-Aware Refinement (RSAR) module iteratively conducting two components: i) a Spatial Transformer Network that dynamically locates an attentional region from the crowd density map and transforms it to the suitable scale and rotation for optimal crowd estimation; ii) a Local Refinement Network that refines the density map of the attended region with residual learning. Extensive experiments on four challenging benchmarks show the effectiveness of our approach. Specifically, comparing with the existing best-performing methods, we achieve an improvement of 12\% on the largest dataset WorldExpo’10 and 22.8\% on the most challenging dataset UCF\_CC\_50

Structured optimal graph based sparse feature extraction for semi-supervised learning

2020 ◽  
Vol 170 ◽  
pp. 107456 ◽  
Author(s):  
Zhonghua Liu ◽  
Zhihui Lai ◽  
Weihua Ou ◽  
Kaibing Zhang ◽  
Ruijuan Zheng
Keyword(s):  
Feature Extraction ◽  
Supervised Learning ◽  
Optimal Graph

scholarly journals Target Detection Network for SAR Images Based on Semi-Supervised Learning and Attention Mechanism

2021 ◽  
Vol 13 (14) ◽  
pp. 2686
Author(s):  
Di Wei ◽  
Yuang Du ◽  
Lan Du ◽  
Lu Li
Keyword(s):  
Feature Extraction ◽  
Supervised Learning ◽  
Target Detection ◽  
Scene Recognition ◽  
Attention Mechanism ◽  
Sar Image ◽  
Target Level ◽  
Sar Images ◽  
Training Samples ◽  
Pass Through

The existing Synthetic Aperture Radar (SAR) image target detection methods based on convolutional neural networks (CNNs) have achieved remarkable performance, but these methods require a large number of target-level labeled training samples to train the network. Moreover, some clutter is very similar to targets in SAR images with complex scenes, making the target detection task very difficult. Therefore, a SAR target detection network based on a semi-supervised learning and attention mechanism is proposed in this paper. Since the image-level label simply marks whether the image contains the target of interest or not, which is easier to be labeled than the target-level label, the proposed method uses a small number of target-level labeled training samples and a large number of image-level labeled training samples to train the network with a semi-supervised learning algorithm. The proposed network consists of a detection branch and a scene recognition branch with a feature extraction module and an attention module shared between these two branches. The feature extraction module can extract the deep features of the input SAR images, and the attention module can guide the network to focus on the target of interest while suppressing the clutter. During the semi-supervised learning process, the target-level labeled training samples will pass through the detection branch, while the image-level labeled training samples will pass through the scene recognition branch. During the test process, considering the help of global scene information in SAR images for detection, a novel coarse-to-fine detection procedure is proposed. After the coarse scene recognition determining whether the input SAR image contains the target of interest or not, the fine target detection is performed on the image that may contain the target. The experimental results based on the measured SAR dataset demonstrate that the proposed method can achieve better performance than the existing methods.

scholarly journals Convolutional Neural Network for Crowd Counting on Metro Platforms

Symmetry ◽  
2021 ◽  
Vol 13 (4) ◽  
pp. 703
Author(s):  
Jun Zhang ◽  
Jiaze Liu ◽  
Zhizhong Wang
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Estimation Error ◽  
Image Features ◽  
Urban Rail Transit ◽  
Crowd Counting ◽  
Passenger Flow ◽  
Urban Rail ◽  
Density Map ◽  
Flow Detection

Owing to the increased use of urban rail transit, the flow of passengers on metro platforms tends to increase sharply during peak periods. Monitoring passenger flow in such areas is important for security-related reasons. In this paper, in order to solve the problem of metro platform passenger flow detection, we propose a CNN (convolutional neural network)-based network called the MP (metro platform)-CNN to accurately count people on metro platforms. The proposed method is composed of three major components: a group of convolutional neural networks is used on the front end to extract image features, a multiscale feature extraction module is used to enhance multiscale features, and transposed convolution is used for upsampling to generate a high-quality density map. Currently, existing crowd-counting datasets do not adequately cover all of the challenging situations considered in this study. Therefore, we collected images from surveillance videos of a metro platform to form a dataset containing 627 images, with 9243 annotated heads. The results of the extensive experiments showed that our method performed well on the self-built dataset and the estimation error was minimum. Moreover, the proposed method could compete with other methods on four standard crowd-counting datasets.

scholarly journals A Novel Domain Adaptation-Based Intelligent Fault Diagnosis Model to Handle Sample Class Imbalanced Problem

Sensors ◽  
2021 ◽  
Vol 21 (10) ◽  
pp. 3382
Author(s):  
Zhongwei Zhang ◽  
Mingyu Shao ◽  
Liping Wang ◽  
Sujuan Shao ◽  
Chicheng Ma
Keyword(s):  
Fault Diagnosis ◽  
Domain Adaptation ◽  
Class Imbalance ◽  
Rolling Bearing ◽  
Industrial Applications ◽  
Mechanical Equipment ◽  
Reliable Operation ◽  
Cross Domain ◽  
Geometric Difference ◽  
Model Generalization

As the key component to transmit power and torque, the fault diagnosis of rotating machinery is crucial to guarantee the reliable operation of mechanical equipment. Regrettably, sample class imbalance is a common phenomenon in industrial applications, which causes large cross-domain distribution discrepancies for domain adaptation (DA) and results in performance degradation for most of the existing mechanical fault diagnosis approaches. To address this issue, a novel DA approach that simultaneously reduces the cross-domain distribution difference and the geometric difference is proposed, which is defined as MRMI. This work contains three parts to improve the sample class imbalance issue: (1) A novel distance metric method (MVD) is proposed and applied to improve the performance of marginal distribution adaptation. (2) Manifold regularization is combined with instance reweighting to simultaneously explore the intrinsic manifold structure and remove irrelevant source-domain samples adaptively. (3) The ℓ2-norm regularization is applied as the data preprocessing tool to improve the model generalization performance. The gear and rolling bearing datasets with class imbalanced samples are applied to validate the reliability of MRMI. According to the fault diagnosis results, MRMI can significantly outperform competitive approaches under the condition of sample class imbalance.

Sign in / Sign up

Export Citation Format

Share Document