Hierarchical Online Instance Matching for Person Search

Chen, Di; Zhang, Shanshan; Ouyang, Wanli; Yang, Jian; Schiele, Bernt

doi:10.1609/aaai.v34i07.6623

Cited by 61 publications

(20 citation statements)

References 38 publications

(53 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compare our framework with state-of-the-art one-step models [2], [50], [9], [10], [74], [11], [19], [12], [77], [63], [71] and two-step models [7], [8], [20], [62], [49]. matching strategy as post-processing to achieve its best performance, while ROI-AlignPS does not need such a process.…”

Section: E Comparison To State-of-the-art Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Efficient Person Search: An Anchor-Free Approach

Yan¹,

Li²,

Qin³

et al. 2021

Preprint

View full text Add to dashboard Cite

Person search aims to simultaneously localize and identify a query person from realistic, uncropped images. To achieve this goal, state-of-the-art models typically add a re-id branch upon two-stage detectors like Faster R-CNN. Owing to the ROI-Align operation, this pipeline yields promising accuracy as re-id features are explicitly aligned with the corresponding object regions, but in the meantime, it introduces high computational overhead due to dense object anchors. In this work, we present an anchor-free approach to efficiently tackling this challenging task, by introducing the following dedicated designs. First, we select an anchor-free detector (i.e., FCOS) as the prototype of our framework. Due to the lack of dense object anchors, it exhibits significantly higher efficiency compared with existing person search models. Second, when directly accommodating this anchor-free detector for person search, there exist several major challenges in learning robust re-id features, which we summarize as the misalignment issues in different levels (i.e., scale, region, and task). To address these issues, we propose an aligned feature aggregation module to generate more discriminative and robust feature embeddings. Accordingly, we name our model as Feature-Aligned Person Search Network (AlignPS). Third, by investigating the advantages of both anchor-based and anchor-free models, we further augment AlignPS with an ROI-Align head, which significantly improves the robustness of re-id features while still keeping our model highly efficient. Extensive experiments conducted on two challenging benchmarks (i.e., CUHK-SYSU and PRW) demonstrate that our framework achieves stateof-the-art or competitive performance, while displaying higher efficiency. All the source codes, data, and trained models are available at: https://github.com/daodaofr/alignps.

show abstract

Section: E Comparison To State-of-the-art Methodsmentioning

confidence: 99%

“…For inference, we rescale the test images to a fixed size of 1500×900. Following [74], we add a focal loss [28] to the original OIM loss. All the experiments are implemented based on PyTorch [75] and MMDetection [76], with an NVIDIA Tesla V100 GPU.…”

Section: B Implementation Detailsmentioning

confidence: 99%

Efficient Person Search: An Anchor-Free Approach

Yan¹,

Li²,

Qin³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…During training, they also propose Online Instance Matching (OIM) loss, which is much more efficient than the cross-entropy loss to train considering the sparse identities of each person in mini-batch. Successively, improved loss functions like Center Loss (Xiao et al 2019), HOIM Loss (Chen et al 2020a) are proposed to better supervise re-ID. Moreover, (Chen et al 2020b) reconciles the contradiction between classification and retrieval by proposing Norm-Aware Embedding (NAE) head, which decouples the embedding features into the norm and angle space for detection and re-ID respectively.…”

Section: Related Work Person Searchmentioning

confidence: 99%

Learning Context-Aware Embedding for Person Search

Chen

Zhuang²,

Li³

2021

Preprint

View full text Add to dashboard Cite

Person Search is a relevant task that aims to jointly solve Person Detection and Person Re-identification (re-ID). Though most previous methods focus on learning robust individual features for retrieval, it's still hard to distinguish confusing persons because of illumination, large pose variance, and occlusion. Contextual information is practically available in person search task which benefits searching in terms of reducing confusion. To this end, we present a novel contextual feature head named Attention Context-Aware Embedding(ACAE) which enhances contextual information. ACAE repeatedly reviews the person features within and across images to find similar pedestrian patterns, allowing it to implicitly learn to find possible co-travelers and efficiently model contextual relevant instances' relations. Moreover, we propose Image Memory Bank to improve the training efficiency. Experimentally, ACAE shows extensive promotion when built on different one-step methods. Our overall methods achieve state-of-the-art results compared with previous one-step methods.

show abstract

“…With the rapid development of deep learning, a growing of researches has been proposed to solve this challenging task. End-to-end methods [1][2][3][4][5][6][7][8] search a target person from the entire scenes, while other methods [9][10][11][12][13][14] divide the task into two separate sub-tasks that are pedestrian detection and person re-identification (Re-ID) respectively. Although there are numerous frameworks designed for person search task, it still faces many challenges and is far from real-world applications.…”

Section: Introductionmentioning

confidence: 99%

Part-Aligned Network with Background for Misaligned Person Search

Zhong

Liu

Huang

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Person search is a significant computer vision task that requires addressing person detection and re-identification simultaneously. Body parts are frequently misaligned due to variation poses, occlusions, and partial missing, leading to the unsatisfied results of person search. Existing methods usually extract local features from the human body by the key point information, that cannot tackle the recognition task between a pair of persons with different body parts due to misalignment. Moreover, these methods overlook background information (e.g. the carries and the background reference object) which can also supplement effective features for representing the person. In this paper, we propose a part-aligned network with background (PANB) to address this misalignment issue. To learn local fine-grained features of different body parts, we fine-tune a parsing network to divide the body region into seven parts. In particular, our proposed method considers extracting the background features as the eighth part features to extract more robust representations, which is more rational and efficient. Furthermore, we design a reconstruction method to align the parts existing in both the query image and the cropped gallery image. Extensive experiments show that our proposed method achieves competitive performance on CUHK-SYSU and PRW datasets.

show abstract

Hierarchical Online Instance Matching for Person Search

Cited by 61 publications

References 38 publications

Efficient Person Search: An Anchor-Free Approach

Efficient Person Search: An Anchor-Free Approach

Learning Context-Aware Embedding for Person Search

Part-Aligned Network with Background for Misaligned Person Search

Contact Info

Product

Resources

About