Densely Semantically Aligned Person Re-Identification

Zhang, Zhizheng; Lan, Cuiling; Zeng, Wenjun; Chen, Zhibo

doi:10.1109/cvpr.2019.00076

Cited by 273 publications

(194 citation statements)

References 63 publications

Supporting

Mentioning

189

Contrasting

Order By: Relevance

“…The softmax output is supervised by the ID label of the training images through the cross-entropy loss. Employing extra crossentropy loss slightly improves the re-ID accuracy of both VANet and the baseline, which is consistent with [1,35].…”

Section: Datasets and Settingssupporting

confidence: 78%

See 1 more Smart Citation

Vehicle Re-Identification With Viewpoint-Aware Metric Learning

Chu

Sun

Li³

et al. 2019

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

175

114

View full text Add to dashboard Cite

This paper considers vehicle re-identification (re-ID) problem. The extreme viewpoint variation (up to 180 degrees) poses great challenges for existing approaches. Inspired by the behavior in human's recognition process, we propose a novel viewpoint-aware metric learning approach. It learns two metrics for similar viewpoints and different viewpoints in two feature spaces, respectively, giving rise to viewpoint-aware network (VANet). During training, two types of constraints are applied jointly. During inference, viewpoint is firstly estimated and the corresponding metric is used. Experimental results confirm that VANet significantly improves re-ID accuracy, especially when the pair is observed from different viewpoints. Our method establishes the new state-of-the-art on two benchmarks. 12 * Corresponding author 1 R. Chu and Y. Sun share equal contribution. 2 Work done at Megvii Technology.

show abstract

Section: Datasets and Settingssupporting

confidence: 78%

“…In addition to the triplet loss, we adopt a cross-entropy loss, following several recent re-ID methods [1,35]. Specifically, we append an ID-classifier upon the featureembedding layer.…”

Section: Datasets and Settingsmentioning

confidence: 99%

Vehicle Re-Identification With Viewpoint-Aware Metric Learning

Chu

Sun

Li³

et al. 2019

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

175

114

View full text Add to dashboard Cite

show abstract

“…[42,43,27] devise attention mechanisms to focus feature learning on the foreground person regions. In [74,44,63,46,51,73], body part-specific CNNs are learned by means of off-the-shelf pose detectors. In [26,23,75], CNNs are branched to learn representations of global and local image regions.…”

Section: Related Work Deep Reid Architecturesmentioning

confidence: 99%

Omni-Scale Feature Learning for Person Re-Identification

Zhou

Yang

Cavallaro

et al. 2019

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

717

351

View full text Add to dashboard Cite

As an instance-level recognition problem, person reidentification (ReID) relies on discriminative features, which not only capture different spatial scales but also encapsulate an arbitrary combination of multiple scales. We callse features of both homogeneous and heterogeneous scales omni-scale features. In this paper, a novel deep ReID CNN is designed, termed Omni-Scale Network (OSNet), for omni-scale feature learning. This is achieved by designing a residual block composed of multiple convolutional feature streams, each detecting features at a certain scale. Importantly, a novel unified aggregation gate is introduced to dynamically fuse multiscale features with input-dependent channel-wise weights. To efficiently learn spatial-channel correlations and avoid overfitting, the building block uses both pointwise and depthwise convolutions. By stacking such blocks layerby-layer, our OSNet is extremely lightweight and can be trained from scratch on existing ReID benchmarks. Despite its small model size, our OSNet achieves state-ofthe-art performance on six person-ReID datasets. Code and models are available at: https://github.com/ KaiyangZhou/deep-person-reid.

show abstract

“…When realizing the limitation of purely global feature learning, many attempts to local feature learning haven arisen. Some methods [7], [6], [33], [18], [34] refer to external clues of pose estimation or body part parsing to extract body part features of persons. [7], [6] utilize the structural part by pose estimation prediction to form relatively precise local region proposals for further representations.…”

Section: Related Workmentioning

confidence: 99%

Receptive Multi-Granularity Representation for Person Re-Identification

Wang

Yuan

et al. 2020

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

A key for person re-identification is achieving consistent local details for discriminative representation across variable environments. Current stripe-based feature learning approaches have delivered impressive accuracy, but do not make a proper trade-off between diversity, locality, and robustness, which easily suffers from part semantic inconsistency for the conflict between rigid partition and misalignment. This paper proposes a receptive multi-granularity learning approach to facilitate stripe-based feature learning. This approach performs local partition on the intermediate representations to operate receptive region ranges, rather than current approaches on input images or output features, thus can enhance the representation of locality while remaining proper local association. Toward this end, the local partitions are adaptively pooled by using significance-balanced activations for uniform stripes. Random shifting augmentation is further introduced for a higher variance of person appearing regions within bounding boxes to ease misalignment. By twobranch network architecture, different scales of discriminative identity representation can be learned. In this way, our model can provide a more comprehensive and efficient feature representation without larger model storage costs. Extensive experiments on intra-dataset and cross-dataset evaluations demonstrate the effectiveness of the proposed approach. Especially, our approach achieves a state-of-the-art accuracy of 96.2%@Rank-1 or 90.0%@mAP on the challenging Market-1501 benchmark.

show abstract

Densely Semantically Aligned Person Re-Identification

Cited by 273 publications

References 63 publications

Vehicle Re-Identification With Viewpoint-Aware Metric Learning

Vehicle Re-Identification With Viewpoint-Aware Metric Learning

Omni-Scale Feature Learning for Person Re-Identification

Receptive Multi-Granularity Representation for Person Re-Identification

Contact Info

Product

Resources

About