Learning Discriminative Features with Multiple Granularities for Person Re-Identification

By Guanshuo Wang, Yufeng Yuan, Xiong Chen, Jiwei Li, Xi Zhou. 2018

1,502 citations recorded by the source corpus.

The combination of global and partial features has been an essential solution to improve discriminative performances in person re-identification (Re-ID) tasks. Previous part-based methods mainly focus on locating regions with specific pre-defined semantics to learn local representations, which increases learning difficulty but not efficient or robust to scenarios with large variances. In this paper, we propose an end-to-end feature learning strategy integrating discriminative information with various granularities. We carefully design the Multiple Granularity Network (MGN), a multi-branch deep network architecture consisting of one branch for global feature representations and two branches for local feature representations. Instead of learning on semantic regions, we uniformly partition the images into several stripes, and vary the number of parts in different local branches to obtain local feature representations with multiple granularities. Comprehensive experiments implemented on the mainstream evaluation datasets including Market-1501, DukeMTMC-reid and CUHK03 indicate that our method robustly achieves state-of-the-art performances and outperforms any existing approaches by a large margin. For example, on Market-1501 dataset in single query mode, we obtain a top result of Rank-1/mAP=96.6%/94.2% with this method after re-ranking.

Subfields: Computer Vision and Pattern Recognition, Ocean Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Ocean Engineering

Citations in the corpus

DISCO: Dynamic and Invariant Sensitive Channel Obfuscation for deep neural networks (2020, methodology): “While sophisticated learning based partitioning methods have been explored [36, 37, 38, 39], methods such as [40] have achieved outstanding performance with trivial deterministic splitting.”
Identity-Guided Human Semantic Parsing for Person Re-Identification (2020, methodology): “Some researchers directly partition the person image into rigid horizontal stripes to learn local features [38, 43, 52, 55].”
Omni-Scale Feature Learning for Person Re-Identification (2019, methodology): “To exploit the upright body pose, [43, 63, 8, 50] add auxiliary supervision signals to features pooled horizontally from the last convolutional feature maps.”
BoT-SORT: Robust Associations Multi-Pedestrian Tracking (2022, background): “Discriminating and re-identifying (ReID) objects by deep-appearance cues [43, 61, 28] has also become popular, but falls short in many cases, especially when scenes are crowded, due to partial occlusions of persons.”
Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification (2020, methodology): “These challenges make it difficult to reliably learn discriminative part-level features using state-of-the-art single-modality Re-ID systems [40,45,55,67].”
ABD-Net: Attentive but Diverse Person Re-Identification (2019, methodology): “Unless otherwise specified, we use ResNet-50 as the default backbone network due to its popularity in Re-ID [45, 46, 47, 48, 49, 11, 50, 51].”
Attribute Prototype Network for Zero-Shot Learning (2020, background): “Local features have been extensively investigated for representation learning [14, 40, 27], and are commonly used in person re-identiﬁcation [34, 38], image captioning [2, 22] and ﬁne-grained classiﬁcation [52, 10, 51].”
Pyramidal Person Re-IDentification via Multi-Loss Dynamic Training (2018, methodology): “In fact, many existing Re-ID methods [26] also beneﬁt from the multi-loss scheme to improve the performance.”
CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels (2022, methodology): “MGN (Wang et al. 2018) utilizes a multiple granularity scheme on feature division to enhance its expressive capabilities further, and it has several branches to capture features from different parts.”
ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis (2020, background): “It is often applied to images, and has found numerous applications such as visual products retrieval [16,23,1], person re-identification [37,30], face recognition [22], few-shot learning [28,14], and clustering [11].”
Self-Similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-Identification (2018, methodology): “Despite the dramatic performance improvement obtained by the convolutional neural network [20, 36, 38], it is reported that deep re-ID models trained on the source domain Self-space C”
Hierarchical Clustering With Hard-Batch Triplet Loss for Person Re-Identification (2019, background): “With the development of convolutional neural networks (CNN), supervised re-ID [9, 11, 21, 25, 30, 2, 31, 23] has achieved excellent performance.”
Circle Loss: A Unified Perspective of Pair Similarity Optimization (2020, methodology): “MGN [31] is one of the state-of-the-art methods and is featured for learning multi-granularity part-level features.”
Deep Learning for Person Re-Identification: A Survey and Outlook (2020, methodology): “Speciﬁcally, we include PCB [68], MGN [179], Auto-ReID [144], ABD-Net [137], BagTricks [151], OSNet [143], DGNet [117], SCAL [83], MHN [101], P2Net [100], BDB [121], SONA [102], SFT [89], ConsAtt [87], DenseS [99], Pyramid [162], IANet [103].”
GaitSet: Regarding Gait as a Set for Cross-View Gait Recognition (2018, methodology): “Since then, set-based methods have been wildly used in point cloud ﬁeld (Wang et al. 2018c; Zhou and Tuzel 2018; Qi et al. 2017).”
TransReID: Transformer-based Object Re-Identification (2021, methodology): “Methods like PCB [32], MGN [37], AlignedReID++ [24], SAN [28], etc, divide an image into several stripes and extract local features for each stripe.”