Sequential End-to-end Network for Efficient Person Search

  title={Sequential End-to-end Network for Efficient Person Search},
  author={Zhengjia Li and Duoqian Miao},
  booktitle={AAAI Conference on Artificial Intelligence},
  • Zhengjia LiD. Miao
  • Published in
    AAAI Conference on Artificial…
    18 March 2021
  • Computer Science
Person search aims at jointly solving Person Detection and Person Re-identification (re-ID). Existing works have designed end-to-end networks based on Faster R-CNN. However, due to the parallel structure of Faster R-CNN, the extracted features come from the low-quality proposals generated by the Region Proposal Network, rather than the detected high-quality bounding boxes. Person search is a fine-grained task and such inferior features will significantly reduce re-ID performance. To address… 

Figures and Tables from this paper

Joint Sample Enhancement and Instance-Sensitive Feature Learning for Efficient Person Search

A novel sample-enhanced and instance-sensitive (SEIE) framework is designed to boost performance and obtain a more efficient and discriminative person search framework by concatenating the two stages.

Sequential Transformer for End-to-End Person Search

The proposed SeqTR not only outperforms all existing person search methods with a 59.3% mAP on PRW but also achieves comparable performance to the state-of-the-art results with an mAP of 94.8% on CUHK-SYSU.

Gallery Filter Network for Person Search

The base SeqNeXt person search model is developed, which improves and simplifies the original SeqNet model, and the Gallery Filter Network is described and demonstrated, a novel module which can discard gallery scenes from the search process and benefit scoring for persons detected in remaining scenes.

PS-ARM: An End-to-End Attention-aware Relation Mixer Network for Person Search

A novel attention-aware relation mixer (ARM) module for person search, which exploits the global relation between different local regions within RoI of a person and make it robust against various appearance deformations and occlusion.

Dual-Attention-Driven Multiscale Fusion Object Searching Network for Remote Sensing Imagery

  • Haolong FuQingpeng Li Zhiyong Li
  • Computer Science, Environmental Science
    IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • 2022
A new end-to-end deep learning framework for object search in remote sensing images is proposed, which strengthens the representation of low-level features by fusing multilayer features and proposes a dual-attention object enhancement module to enhance features from channel and spatial dimensions.

Person Search via Background and Foreground Contrastive Learning

  • Qing TangK. Jo
  • Computer Science
    2022 15th International Conference on Human System Interaction (HSI)
  • 2022
The proposed Background and Foreground Contrastive Loss (BFCL) is proposed to strengthen the learning of distinguishing similar background and foreground by leveraging inter-RoIs pairwise similarity and consistently boosts the performance of the baseline framework SeqNet in two datasets.

PSTR: End-to-End One-Step Person Search With Transformers

  • Jiale CaoYanwei Pang F. Khan
  • Computer Science
    2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2022
The proposed PSTR is the first to propose an end-to-end one-step transformer-based person search framework that jointly performs person detection and re-identification (re-id) in a single architecture and sets a new state-of-the-art on both benchmarks.

Cascade Transformers for End-to-End Person Search

  • Rui YuDawei Du Brian Clipp
  • Computer Science
    2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2022
The Cascade Occluded Attention Transformer (COAT) for end-to-end person search uses a three-stage cascade design that focuses on detecting people in the first stage, while later stages simultaneously and progressively refine the representation for person detection and re-identification.

Global-Local Context Network for Person Search

This paper delves into the rich context information globally and locally surrounding the target person, which it refers to scene and group context, respectively, and exploits them in a global-local context network (GLCNet) with the intuitive aim of feature enhancement.

Domain Adaptive Person Search

This paper presents Domain Adaptive Person Search (DAPS), which aims to generalize the model from a labeled source domain to the unlabeled target domain, and surpasses some of the fully and weakly supervised methods.



Query-Guided End-To-End Person Search

A novel query-guided end-to-end person search network (QEEPS) to address both person detection and re-identification and outperform the previous state-of-the-art datasets by a large margin.

Joint Detection and Identification Feature Learning for Person Search

A new deep learning framework for person search that jointly handles pedestrian detection and person re-identification in a single convolutional neural network and converges much faster and better than the conventional Softmax loss.

Person Re-identification in the Wild

A new dataset, PRW, is introduced to evaluate Person Re-identification in the Wild, and it is shown that pedestrian detection aids re-ID through two simple yet effective improvements: a cascaded fine-tuning strategy that trains a detection model first and then the classification model, and a Confidence Weighted Similarity (CWS) metric that incorporates detection scores into similarity measurement.

Random Erasing Data Augmentation

In training, Random Erasing randomly selects a rectangle region in an image and erases its pixels with random values and yields consistent improvement over strong baselines in image classification, object detection and person re-identification.

In Defense of the Triplet Loss for Person Re-Identification

It is shown that, for models trained from scratch as well as pretrained ones, using a variant of the triplet loss to perform end-to-end deep metric learning outperforms most other published methods by a large margin.

Bi-Directional Interaction Network for Person Search

This work proposes a Siamese network which owns an additional instance-aware branch, named Bi-directional Interaction Network (BINet), which achieves state-of-the-art results among end-to-end methods without loss of efficiency.

TCTS: A Task-Consistent Two-Stage Framework for Person Search

A Task-Consist Two-Stage (TCTS) person search framework, which includes an identity-guided query (IDGQ) detector and a Detection Results Adapted (DRA) re-ID model, outperforming the previous state of the art methods.

Instance Guided Proposal Network for Person Search

A new detection network for person search, named Instance Guided Proposal Network (IGPN), which can learn the similarity between query persons and proposals and can decrease proposals according to the similarity scores is proposed.

Norm-Aware Embedding for Efficient Person Search

A novel approach called Norm-Aware Embedding is presented to disentangle the person embedding into norm and angle for detection and re-ID respectively, allowing for both effective and efficient multi-task training.

Hierarchical Online Instance Matching for Person Search

A Hierarchical Online Instance Matching (HOIM) loss is proposed which exploits the hierarchical relationship between detection and re-ID to guide the learning of the network and justifies the effectiveness of the proposed HOIM loss on learning robust features.