Discriminative Feature Learning With Foreground Attention for Person Re-Identification

Zhou, Sanping; Wang, Jinjun; Meng, Deyu; Liang, Yudong; Gong, Yi; Zheng, Nanning

doi:10.1109/tip.2019.2908065

Cited by 63 publications

(13 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…bounding-boxes or masks of instances) than the overall count which is computational expensive and mostly suitable in lower density crowds. In overcrowded scenes, clutters and severe occlusions make it unfeasible to detect every single person, despite the progresses in related fields [19,10,47,17,33,43,61,50,48,34,49,55,60,52]. Secondly, training object detectors require bounding-box or instance mask annotations, which is much more labor-intensive in dense crowds.…”

Section: Related Workmentioning

confidence: 99%

Bayesian Loss for Crowd Count Estimation With Point Supervision

Wei

Hong

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

Self Cite

475

344

View full text Add to dashboard Cite

In crowd counting datasets, each person is annotated by a point, which is usually the center of the head. And the task is to estimate the total count in a crowd scene. Most of the state-of-the-art methods are based on density map estimation, which convert the sparse point annotations into a "ground truth" density map through a Gaussian kernel, and then use it as the learning target to train a density map estimator. However, such a "ground-truth" density map is imperfect due to occlusions, perspective effects, variations in object shapes, etc. On the contrary, we propose Bayesian loss, a novel loss function which constructs a density contribution probability model from the point annotations. Instead of constraining the value at every pixel in the density map, the proposed training loss adopts a more reliable supervision on the count expectation at each annotated point. Without bells and whistles, the loss function makes substantial improvements over the baseline loss on all tested datasets. Moreover, our proposed loss function equipped with a standard backbone network, without using any external detectors or multi-scale architectures, plays favourably against the state of the arts. Our method outperforms previous best approaches by a large margin on the latest and largest UCF-QNRF dataset. The source code is available at https://github.com/ZhihengCV/ Baysian-Crowd-Counting. arXiv:1908.03684v1 [cs.CV] 10 Aug 2019 pixel, our proposed training loss supervises on the count expectation at each annotated point, instead.Extensive experimental evaluations show that the proposed loss function substantially outperforms the baseline training loss on UCF-QNRF [16], ShanghaiTech [57], and UCF CC 50 [15] benchmark datasets. Moreover, our proposed loss function equipped with the standard VGG-19 network [39] as backbone, without using any external detectors or multi-scale architectures, achieves the state-ofthe-art performances on all the benchmark datasets, especially with a magnificent improvement on the UCF-QNRF dataset compared to other methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Bayesian Loss for Crowd Count Estimation With Point Supervision

Wei

Hong

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

Self Cite

475

344

View full text Add to dashboard Cite

show abstract

“…Author in [35] proposed a Pyramid Person Matching Network to learn the correspondence of misalignment components in image pairs. Attention mechanisms are applied in many models [20][21][22][23] to focus on salient parts to extract more useful and discriminative information. Recent studies start to consider part-level features as complementary features for their models due to its finegrained information.…”

Section: B Cnn-based Re-idmentioning

confidence: 99%

“…In recent years, with the growth of convolutional neural networks (CNNs) and careful-annotated benchmarks, CNN-based models which learn deep features from data outperform hand-crafted methods by a large margin and achieve remarkable accuracy [12]. To obtain more discriminative features to deal with the inter-class challenge, some works try to extract local features from local regions in different ways, such as pose normalization [13][14][15], part-based learning [16][17][18][19], or attention mechanism [20][21][22][23]. Although these great works gain very high performance in accuracy and mAP, they are still only employed deep features, which do not contain semantic information and cannot be explained by human.…”

Section: Introductionmentioning

confidence: 99%

Person Re-Identification System at Semantic Level based on Pedestrian Attributes Ontology

Ly¹,

Cao²,

Nguyen³

2020

IJACSA

View full text Add to dashboard Cite

Person Re-Identification (Re-ID) is a very important task in video surveillance systems such as tracking people, finding people in public places, or analysing customer behavior in supermarkets. Although there have been many works to solve this problem, there are still remaining challenges such as large-scale datasets, imbalanced data, viewpoint, finegrained data (attributes), the Local Features are not employed at semantic level in online stage of Re-ID task, furthermore, the imbalanced data problem of attributes are not taken into consideration. This paper has proposed a Unified Re-ID system consisted of three main modules such as Pedestrian Attribute Ontology (PAO), Local Multi-task DCNN (Local MDCNN), Imbalance Data Solver (IDS). The new main point of our Re-ID system is the power of mutual support of PAO, Local MDCNN and IDS to exploit the inner-group correlations of attributes and pre-filter the mismatch candidates from Gallery set based on semantic information as Fashion Attributes and Facial Attributes, to solve the imbalanced data of attributes without adjusting network architecture and data augmentation. We experimented on the well-known Market1501 dataset. The experimental results have shown the effectiveness of our Re-ID system and it could achieve the higher performance on Market1501 dataset in comparison to some state-of-the-art Re-ID methods.

show abstract

“…Person REID attracts much more research interest by the development of deep learning technology in recent years. The related models are classified as global-based [8], [9], and part-based feature representations [18]- [20].…”

Section: Related Work a Image Based Person Re-identificationmentioning

confidence: 99%

“…Most of the proposed methods make an assumption that all pedestrian images have sufficiently high resolution captured by a variety of cameras [8], [9]. However, the distances The associate editor coordinating the review of this manuscript and approving it for publication was Gianluigi Ciocca .…”

Section: Introductionmentioning

confidence: 99%

Part-Based Enhanced Super Resolution Network for Low-Resolution Person Re-Identification

Tian

Miao

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Person re-identification (REID) is an important task in video surveillance and forensics applications. Many previous works often build models on the assumption that they have same resolution cross different camera views, while it is divorced from reality. To increase the adaptability of person REID models, this paper focuses on the low-resolution person REID task to relax the impractical assumption when traditional low-resolution person REID models are under pixel-to-pixel supervision in low and high resolution pedestrian image pairs. In addition, they are easily influenced by the global background, illumination or pose variations across camera views. Therefore, we propose a Part-based Enhanced Super Resolution (PESR) network by employing a part division strategy and an enhanced generative adversarial network to boost the unpaired pedestrian image super resolution process. Specifically, the part-based super resolution network transforms low resolution image in probe into high resolution without any pixel-to-pixel supervision and the part-based synthetic feature extractor module can learn discriminative pedestrian feature representation for the generated high resolution images, which employ a part feature connection loss as constraint to conduct matching for person re-identification. Furthermore, evaluations on four public person REID datasets demonstrate the advantages of our method over the state-of-the-art ones. INDEX TERMS Low-resolution person re-identification, enhanced super resolution, part based, realistic discriminator.

show abstract

Discriminative Feature Learning With Foreground Attention for Person Re-Identification

Cited by 63 publications

References 70 publications

Bayesian Loss for Crowd Count Estimation With Point Supervision

Bayesian Loss for Crowd Count Estimation With Point Supervision

Person Re-Identification System at Semantic Level based on Pedestrian Attributes Ontology

Part-Based Enhanced Super Resolution Network for Low-Resolution Person Re-Identification

Contact Info

Product

Resources

About