Performance Of Person Re-identification Research Articles

Multi-Domain Adversarial Feature Generalization for Person Re-Identification.

With the assistance of sophisticated training methods applied to single labeled datasets, the performance of fully-supervised person re-identification (Person Re-ID) has been improved significantly in recent years. However, these models trained on a single dataset usually suffer from considerable performance degradation when applied to videos of a different camera network. To make Person Re-ID systems more practical and scalable, several cross-dataset domain adaptation methods have been proposed, which achieve high performance without the labeled data from the target domain. However, these approaches still require the unlabeled data of the target domain during the training process, making them impractical. A practical Person Re-ID system pre-trained on other datasets should start running immediately after deployment on a new site without having to wait until sufficient images or videos are collected and the pre-trained model is tuned. To serve this purpose, in this paper, we reformulate person re-identification as a multi-dataset domain generalization problem. We propose a multi-dataset feature generalization network (MMFA-AAE), which is capable of learning a universal domain-invariant feature representation from multiple labeled datasets and generalizing it to 'unseen' camera systems. The network is based on an adversarial auto-encoder to learn a generalized domain-invariant latent feature representation with the Maximum Mean Discrepancy (MMD) measure to align the distributions across multiple domains. Extensive experiments demonstrate the effectiveness of the proposed method. Our MMFA-AAE approach not only outperforms most of the domain generalization Person Re-ID methods, but also surpasses many state-of-the-art supervised methods and unsupervised domain adaptation methods by a large margin.

Person Re-Identification Based on Joint Loss and Multiple Attention Mechanism

Person re-identification (ReID) is the use of computer vision and machine learning techniques to determine whether the pedestrians in the two images under different cameras are the same person. It can also be regarded as a matching retrieval task for person targets in different scenes. The research focuses on how to obtain effective person features from images with occlusion, angle change, and target attitude change. Based on the present difficulties and challenges in ReID, the paper proposes a ReID method based on joint loss and multi-attention network. It improves the person re-identification algorithm based on global characteristics, introduces spatial attention and channel attention and constructs joint loss function, improving the characteristic extraction ability of the network and improving the model performance of person re-identification. It analyzes the validity and necessity of each module of the algorithm through the ablation experiment. In addition, it carries out training and evaluation on the two person re-recognition data sets Market1501 and MSMT17, and verifies the advantages of the proposed algorithm in contrast to other advanced algorithms.

Style transfer for unsupervised domain-adaptive person re-identification

Person re-identification (Re-ID) is aimed to identify the same person under different cameras with disjoint views. With the development of deep learning, supervised Re-ID has made great progress. However, most methods fail to be generalized to new domains due to the potential image distinctions between different domains, making it difficult to be applied in practical use. We propose an unsupervised domain-adaptive person re-identification method based on style transfer (STReID) to improve model cross-domain capability. In this work, a novel style transfer framework is proposed for Re-ID, which allows us to change the style of images while retaining content information. Specifically, STReID mainly includes two steps: first, each image in the source domain is converted into the target domain style and the identity (ID) information remains unchanged. Then the source domain images and style transferred images are combined to train a style-independent Re-ID model. Experiments show that our method achieves higher performance of unsupervised cross-domain person Re-ID.

A unified framework for automated person re-indentification

Along with the strong development of camera networks, a video analysis system has been become more and more popular and has been applied in various practical applications. In this paper, we focus on person re-identification (person ReID) task that is a crucial step of video analysis systems. The purpose of person ReID is to associate multiple images of a given person when moving in a non-overlapping camera network. Many efforts have been made to person ReID. However, most of studies on person ReID only deal with well-alignment bounding boxes which are detected manually and considered as the perfect inputs for person ReID. In fact, when building a fully automated person ReID system the quality of the two previous steps that are person detection and tracking may have a strong effect on the person ReID performance. The contribution of this paper are two-folds. First, a unified framework for person ReID based on deep learning models is proposed. In this framework, the coupling of a deep neural network for person detection and a deep-learning-based tracking method is used. Besides, features extracted from an improved ResNet architecture are proposed for person representation to achieve a higher ReID accuracy. Second, our self-built dataset is introduced and employed for evaluation of all three steps in the fully automated person ReID framework.

A unified framework for automated person re-identification

Along with the strong development of camera networks, a video analysis system has been become more and more popular and has been applied in various practical applications. In this paper, we focus on person re-identification (person ReID) task that is a crucial step of video analysis systems. The purpose of person ReID is to associate multiple images of a given person when moving in a non-overlapping camera network. Many efforts have been made to person ReID. However, most of studies on person ReID only deal with well-alignment bounding boxes which are detected manually and considered as the perfect inputs for person ReID. In fact, when building a fully automated person ReID system the quality of the two previous steps that are person detection and tracking may have a strong effect on the person ReID performance. The contribution of this paper are two-folds. First, a unified framework for person ReID based on deep learning models is proposed. In this framework, the coupling of a deep neural network for person detection and a deep-learning-based tracking method is used. Besides, features extracted from an improved ResNet architecture are proposed for person representation to achieve a higher ReID accuracy. Second, our self-built dataset is introduced and employed for evaluation of all three steps in the fully automated person ReID framework.

Projection with Gaussian Kernel for Person Re-Identification

Person re-identification (ReID), the task of associating the detected images of a person as he/she moves in a non-overlapping camera network, is faced with different challenges including variations in the illumination, view-point and occlusion. To ensure good performance for person ReID, the state-of-the-art methods have leveraged different characteristics for person representation. As a result, a high-dimensional feature vector is extracted and used in the person matching step. However, each feature plays a specific role for distinguishing one person from the others. This paper proposes a method for person ReID wherein the correspondences between descriptors in high-dimensional space can be achieved via explicit feature selection and appropriate projection with a Gaussian kernel. The advantage of the proposed method is that it allows simultaneous matching of the descriptors while preserving the local geometry of the manifolds. Different experiments were conducted on both single-shot and multi-shot person ReID datasets. The experimental results demonstrates that the proposed method outperforms the state-of-the-art methods.

Deep features for person re-identification on metric learning

Person re-identification, a branch of image retrieval, is an increasingly important public safety application. When monitoring larger areas, it is crucial to correctly match the same person in different camera views. With the emergence of deep learning and large-scale data, metric learning has significantly improved person re-identification performance, but the extent to which deep features affect metric learning performance is unknown. However, given the large number of approaches, datasets, evaluation indices, and experimental environments, comparing metric learning methods directly is difficult. To obtain a more comprehensive empirical evaluation of the person re-identification, here we summarize the different types of features and metric learning approaches from a label attributes perspective. Then, by combining advanced approaches to data enhancement and feature extraction, we conduct comprehensive experiments on metric learning methods with two datasets. For fairness, all methods use a unified code library that includes two data enhancement schemes, eight feature extraction algorithms, and eight metric learning methods. Our results show that, the relations of loss function with deep feature space and metric learning.

Video-Based Person Re-Identification With Unregulated Sequences

Video-based person re-identification (re-id) has recently attracted widespread attentions because extra space-time information and more appearance cues in videos can be used to improve the performance of image-based person re-id. Most existing approaches equally treat person video images, ignoring their individual discrepancy. However, in real scenarios, captured images are usually contaminated by various noises, especially occlusions, resulting in a series of unregulated sequences. Through investigating the impact of unregulated sequences to feature representation of video-based person re-id, the authors find a remarkable promotion by eliminating noisy sub sequences. Based on this interesting finding, an adaptive unregulated sub sequence detection and refinement method is proposed to purify original video sequence and obtain a more effective and discriminative feature representation for video-based person re-id. Experimental results on two public datasets demonstrate that the proposed method outperforms the state-of-the-art work.

Cross-level reinforced attention network for person re-identification

Attention mechanism is a simple and effective method to enhance discriminative performance of person re-identification (Re-ID). Most of previous attention-based works have difficulty in eliminating the negative effects of meaningless information. In this paper, a universal module, named Cross-level Reinforced Attention (CLRA), is proposed to alleviate this issue. Firstly, we fuse features of different semantic levels using adaptive weights. The fused features, containing richer spatial and semantic information, can better guide the generation of subsequent attention module. Then, we combine hard and soft attention to improve the ability to extract important information in spatial and channel domains. Through the CLRA, the network can aggregate and propagate more discriminative semantic information. Finally, we integrate the CLRA with Harmonious Attention CNN (HA-CNN) and form a novel Cross-level Reinforced Attention CNN (CLRA-CNN) to optimize person Re-ID. Experiment results on several public benchmarks show that the proposed method achieves state-of-the-art performance.

Deep Fusion Feature Representation Learning With Hard Mining Center-Triplet Loss for Person Re-Identification

Person re-identification (Re-ID) is a challenging task in the field of computer vision and focuses on matching people across images from different cameras. The extraction of robust feature representations from pedestrian images through CNNs with a single deterministic pooling operation is problematic as the features in real pedestrian images are complex and diverse. To address this problem, we propose a novel center-triplet (CT) model that combines the learning of robust feature representation and the optimization of metric loss function. Firstly, we design a fusion feature learning network (FFLN) with a novel fusion strategy consisting of max pooling and average pooling. Instead of adopting a single deterministic pooling operation, the FFLN combines two pooling operations that can learn high response values, bright features, and low response values, discriminative features simultaneously. Our model obtains more discriminative fusion features by adaptively learning the weights of the features learned by the corresponding pooling operations. In addition, we design a hard mining center-triplet loss (HCTL), a novel improved triplet loss, which effectively optimizes the intra/inter-class distance and reduces the cost of computing and mining hard training samples simultaneously, thereby enhancing the learning of robust feature representation. Finally, we proved our method can learn robust and discriminative feature representations for complex pedestrian images in real scenes. The experimental results also illustrate that our method achieves an 81.8% mAP and a 93.8% rank-1 accuracy on Market1501, a 68.2% mAP and an 83.3% rank-1 accuracy on DukeMTMC-ReID, and a 43.6% mAP and a 74.3% rank-1 accuracy on MSMT17, outperforming most state-of-the-art methods and achieving better performance for person re-identification.

Person Re-Identification with Feature Pyramid Optimization and Gradual Background Suppression

Compared with face recognition, the performance of person re-identification (re-ID) is still far from practical application. Among various interferences, there are two factors seriously limiting the performance improvement, i.e., the feature discriminability determined by “external network effectiveness”, and the image quality determined by “internal background clutters”. Target at the “external network effectiveness” problem, feature pyramids are effective to learn discriminative features because they can learn both detailed features from high-resolution shallow layers and semantical features from low-resolution deep layers, however, it can only achieve slight improvement on re-ID tasks because of the error back propagation problem. To handle the problem and utilize the effectiveness of feature pyramids, we propose a strategy called Feature Pyramid Optimization (FPO). Instead of concatenating features directly, the selected layers are optimized independently in a top–bottom order. Target at the “internal background clutters” problem, background suppression is generally considered for removing the environmental interference and improving the image quality. Several mask-based methods are used attempting to totally remove background clutters but achieve limited promotion because of the mask sharpening effect. We propose a novel strategy, i.e., Gradual Background Suppression (GBS) to reduce the background clutters and keep the smoothness of images simultaneously. Extensive experiments have been conducted and the results demonstrate the effectiveness of both FPO and GBS.

Scale-fusion framework for improving video-based person re-identification performance

Video-based person re-identification (re-id), which aims to match people through videos captured by non-overlapping camera views, has attracted lots of research interest recently. In this paper, we first propose a novel hybrid 2D and 3D convolution-based recurrent neural network (HCRN) for video-based person re-id task. Specifically, the 3D convolutional module can explore the local short-term fast-varying motion information, while the recurrent layer can leverage the global long-term spatial–temporal information. Based on HCRN, we design a scale-fusion framework to make full use of features of different scales to further improve the performance of video-based person re-id. More concretely, the scale-fusion framework preserves a complete subnetwork similar to HCRN for each scale to extract features and exchanges information between all subnetworks at several stages of the framework. Besides, we propose a training method called species invasion to further improve the performance of HCRN and scale-fusion framework by utilizing a large amount of unlabeled data. Experimental results on the publicly available PRID 2011, iLIDS-VID and MARS multi-shot pedestrian re-id datasets demonstrate the effectiveness of the proposed HCRN, scale-fusion framework and species invasion training method.

Improving Person Re-identification with Iterative Impression Aggregation.

Our impression about one person often updates after we see more aspects of him/her and this process keeps iterating given more meetings. We formulate such an intuition into the problem of person re-identification (re-ID), where the representation of a query (probe) image is iteratively updated with new information from the candidates in the gallery. Specifically, we propose a simple attentional aggregation formulation to instantiate this idea and showcase that such a pipeline achieves competitive performance on standard benchmarks including CUHK03, Market-1501 and DukeMTMC. Not only does such a simple method improve the performance of the baseline models, it also achieves comparable performance with latest advanced re-ranking methods. Another advantage of this proposal is its flexibility to incorporate different representations and similarity metrics. By utilizing stronger representations and metrics, we further demonstrate state-of-the-art person re-ID performance, which also validates the general applicability of the proposed method.

Pseudo Label Based on Multiple Clustering for Unsupervised Cross-Domain Person Re-Identification

Person re-identification (Re-ID) has achieved great improvement with the development of deep learning. However, domain adaptation in unsupervised Re-ID has always been a challenging task. Most existing works based on clustering only cluster once, which may lead to pseudo labels of poor quality. In this letter, we propose a Pseudo Label based on Multiple Clustering (PLMC) approach, which makes full advantage of multiple clustering to obtain more robust pseudo labels. In particular, our PLMC framework consists of two stages, namely, global training stage, and local training stage. We adopt the training strategy that combines the information learned from global features, and local features by training two stages alternately. Extensive experiments are carried out on three standard benchmark datasets (e.g., Maket1501, DukeMTMC-ReID, CUHK03). The results demonstrate that our PLMC method is superior to the previous methods based on single clustering, and achieves state-of-the-art person Re-ID performance under the unsupervised cross-domain setting.

Generated Data With Sparse Regularized Multi-Pseudo Label for Person Re-Identification

Recently, Generative Adversarial Network (GAN) has been adopted to improve person re-identification (person re-ID) performance through data augmentation. However, directly leveraging generated data to train a re-ID model may easily lead to over-fitting issue on these extra data and decrease the generalisability of model to learn true ID-related features from real data. Inspired by the previous approach which assigns multi-pseudo labels on the generated data to reduce the risk of over-fitting, we propose to take sparse regularization into consideration. We attempt to further improve the performance of current re-ID models by using the unlabeled generated data. The proposed Sparse Regularized Multi-Pseudo Label (SRMpL) can effectively prevent the over-fitting issue when some larger weights are assigned to the generated data. Our experiments are carried out on two publicly available person re-ID datasets (e.g., Market-1501 and DukeMTMC-reID). Compared with existing unlabeled generated data re-ID solutions, our approach achieves competitive performance. Two classical re-ID models are used to verify our sparse regularization label on generated data, i.e., an ID-embedding network and a two-stream network.

Learning Domain-Specific Features From General Features for Person Re-Identification

Person re-identification (re-id) plays a vital role in surveillance and forensics application. Since the labeled images for person re-id task is limited, the generalization ability of existed person re-id models is poor. On the other hand, images of different classes (pedestrian and non-pedestrian images) share some general features. To this end, this paper aims to improve the performance of person re-id by designing a relearning network which can learn domain-specific features and general features simultaneously. The proposed relearning network consists of a pretrained backbone network which provides the general features, and several attention-based subnetworks that learn domain-specific features from general features of different levels. Besides, we propose a coarse-fine loss to improve the generalization of person re-id model by making full use of the massive labeled non-pedestrian images. Experimental results on the publicly available Market-1501, DukeMTMC-reID and CUHK03 pedestrian re-id datasets demonstrate the effectiveness of the proposed relearning network and coarse-fine loss.

Multi Scale-Adaptive Super-Resolution Person Re-Identification Using GAN

In real-world surveillance systems, the person images captured by the camera network consists of various low-resolution (LR) images. It creates a resolution mismatching problem when compared against high-resolution images of a targeted person. It significantly affects the performance of person re-Identification. This problem is known as Low-Resolution Person re-identification (LR PREID). An efficient strategy would be to exploit image super-resolution (SR) with person re-identification as a mutual learning approach. In this paper, we propose a novel method MSA-SR-PREID to solve this problem. The model takes low-resolution images on different resolutions and resized them to pre-defined fixed resolution. The design of the super-resolution network consists of ESRGAN and the de-Noising module to generate super-resolution images. The SR images are later passed to the re-identification network to learn the unique descriptors to recognize a person identity. The performance of this model is evaluated on four competitive benchmarks, MLR-VIPeR, MLR-DukeMTMC-reID, VR-MSMT17, and VR-Market1501. The comparison with similar state-of-the-art demonstrates the superiority of our model.

A Mask-Pooling Model With Local-Level Triplet Loss for Person Re-Identification

Person Re-Identification (ReID) is an important yet challenging task in computer vision. Background clutter is one of the greatest challenges to overcome. In this paper, we propose a Mask-pooling model with local-level triplet loss (MPM-LTL) to tackle this problem and improve person ReID performance. Specifically, we present a novel pooling method, called mask pooling (MP), to gradually remove background features in feature maps through deep convolutional network. With mask pooling, the network can learn the most crucial person features. Moreover, we raise a novel local-level triplet loss for discriminative feature training. Furthermore, we propose a new hard triplets selection algorithm named Mask-guided TriHard. The method is based on human outline information, which is, to our best knowledge, employed for the first time for hard triplets selection. We achieve the state-of-the-art results on three benchmark person datasets Market-1501 [1] , CUHK03 [2] and DukeMTMC-reID [3] , [4] .

Person Re-Identification Using Additive Distance Constraint With Similar Labels Loss

Despite the promising progress made in recent years, person re-identification (Re-ID) remains a challenging task due to the intra-class variations. Most of the current studies used the traditional Softmax loss for solutions, but its discriminative capability encounters a bottleneck. Therefore, how to improve person Re-ID performance is still a challenging task. To address this problem, we proposed a novel loss function, namely additive distance constraint with similar labels loss (ADCSLL). Specifically, we reformulated the Softmax loss by adding a distance constraint to the ground truth label, based on which similar labels were introduced to enhance the learned features to be much more stable and centralized. Experimental evaluations were conducted on two popular datasets (Market-1501 and DukeMTMC-reID) to examine the effectiveness of our proposed method. The results showed that our proposed ADCSLL was more discriminative than most of the other compared state-of-the-art methods. The rank-1 accuracy and the mAP on Market-1501 were 95.0% and 87.0%, respectively. The numbers were 88.6% and 77.2% on DukeMTMC-reID, respectively.

MSBA: Multiple Scales, Branches and Attention Network With Bag of Tricks for Person Re-Identification

Person re-identification (Re-ID) has become a hot topic in both research and industry. We joined in a person Re-ID challenge of the First National Artificial Intelligence Challenge (China, 2019) and found some model designs and training tricks work great or not on a super big private dataset. In this paper, we propose a model that combines the most effective designs, including multi-scale, multi-branch and attention mechanism, and report training tricks that are no less or even more important in improving person Re-ID performance. We analyze four commonly used public datasets: Market1501, DukeMTMC-ReID, CUHK03, and MSMT17, and achieve the state-of-the-art performance. Besides, we analyze and confirm the effectiveness of the designs by ablation studies. We also share strategies that play a key role in the challenge and experience of model designs that do not generalize well on large datasets.