Combined Depth Space based Architecture Search For Person Re-identification

  title={Combined Depth Space based Architecture Search For Person Re-identification},
  author={Hanjun Li and Gaojie Wu and Weishi Zheng},
  journal={2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
Most works on person re-identification (ReID) take advantage of large backbone networks such as ResNet, which are designed for image classification instead of ReID, for feature extraction. However, these backbones may not be computationally efficient or the most suitable architectures for ReID. In this work, we aim to design a lightweight and suitable network for ReID. We propose a novel search space called Combined Depth Space (CDS), based on which we search for an efficient network… 

FPB: Feature Pyramid Branch for Person Re-Identification

This paper proposes a lightweight Feature Pyramid Branch (FPB) to extract features from different layers of networks and aggregate them in a bidirectional pyramid structure, which empirically proves that pyramid network as affiliated branch could be a potential structure in related feature embedding models.

Conditional Feature Embedding by Visual Clue Correspondence Graph for Person Re-Identification

This paper proposes a novel ReID framework that extracts conditional feature embedding based on the aligned visual clues between image pairs, called Clue Alignment based Conditional Embedding (CACE-Net), which applies an attention module to build a detailed correspondence graph between crucial visual clues in image pairs.

Transformer-Based Attention Network for Vehicle Re-Identification

The experimental results demonstrated that the proposed TAN is effective in improving the performance of both the vehicle and person ReID tasks, and the proposed method achieves state-of-the-art (SOTA) perfomance.

VAC-Net: Visual Attention Consistency Network for Person Re-identification

This paper proposes a visual attention consistency network (VAC-Net) with Embedding Spatial Consistency (ESC) architecture with flipping, scaling and original forms of the same image as inputs to learn a consistent embedding space and designs an Input-Wise visual attention consistent loss (IW-loss).

A Survey of Person Re-identification Based on Deep Learning

This paper summarizes and analyzes the latest research trends of person Re-ID based on deep learning and coarsely categorized into the supervised learning methods and the unsupervised learning methods according to whether the pedestrian images in the training set have real labels.

Joint uneven channel information network with blend metric loss for person re-identification

A blend metric loss is proposed to optimize the joint uneven channel information network efficiently and dynamically adjust the penalty for the sample distance and the distance margin based on the outlier of the hardest sample to construct i-TriHard loss.

Cascaded attention-guided multi-granularity feature learning for person re-identification

A novel framework called cascaded attention network (CANet), which allows to mine diverse clues and integrate them into final multi-granularity features by a cascaded manner, and state-of-the-art results are achieved on three public benchmark datasets.

HAT: Hierarchical Aggregation Transformers for Person Re-identification

This work takes advantages of both CNNs and Transformers, and proposes a novel learning framework named Hierarchical Aggregation Transformer (HAT) for image-based person Re-ID with high performance.

DiP: Learning Discriminative Implicit Parts for Person Re-Identification

This work proposes to learn Discriminative implicit Parts (DiPs) which are decoupled from explicit body parts which can learn to extract any discriminative features that can benefit in distin-guishing identities, which is beyond predeflned body parts (such as accessories).

Vehicle Re-Identification with Spatio-Temporal Model Leveraging by Pose View Embedding

A two-branch framework for vehicle Re-ID is designed, including a Keypoint-based Pose Embedding Visual (KPEV) model and a Key pointed Pose-Guided Spatio-Temporal (KPGST) model, which is integrated into the framework and the results of KPEV and KPGST are fused based on a Bayesian network.



Auto-ReID: Searching for a Part-Aware ConvNet for Person Re-Identification

This work proposes a retrieval-based search algorithm over a specifically designed reID search space, named Auto-ReID, which enables the automated approach to find an efficient and effective CNN architecture for reID.

Compact Network Training for Person ReID

This study focuses on a small-sized randomly initialized model that enables us to easily introduce architecture and training modifications suitable for person ReID and shows the robustness of the network by outperforming the SotA on both Market1501 and DukeMTMC.

Pyramidal Person Re-IDentification via Multi-Loss Dynamic Training

A novel coarse-to-fine pyramid model is proposed to relax the need of bounding boxes and learn discriminative identity representation, which not only incorporates local and global information, but also integrates the gradual cues between them.

Faster Person Re-Identification

This work designs an All-in-One (AiO) framework together with a Distance Threshold Optimization (DTO) algorithm, which simultaneously learn and enhance multiple codes of different lengths in a single model, which complementarily uses short and long codes, achieving both faster speed and better accuracy.

Harmonious Attention Network for Person Re-identification

  • Wei LiXiatian ZhuS. Gong
  • Computer Science
    2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
A novel Harmonious Attention CNN (HA-CNN) model is formulated for joint learning of soft pixel attention and hard regional attention along with simultaneous optimisation of feature representations, dedicated to optimise person re-id in uncontrolled (misaligned) images.

Interaction-And-Aggregation Network for Person Re-Identification

A novel network structure, Interaction-and-Aggregation (IA), to enhance the feature representation capability of CNNs and validate the effectiveness of the model by demonstrating its superiority over state-of-the-art methods on three benchmark datasets.

Mask-Guided Contrastive Attention Model for Person Re-identification

This paper introduces the binary segmentation masks to construct synthetic RGB-Mask pairs as inputs, then designs a mask-guided contrastive attention model (MGCAM) to learn features separately from the body and background regions, and proposes a novel region-level triplet loss to restrain the features learnt from different regions.

Scalable Person Re-identification: A Benchmark

A minor contribution, inspired by recent advances in large-scale image search, an unsupervised Bag-of-Words descriptor is proposed that yields competitive accuracy on VIPeR, CUHK03, and Market-1501 datasets, and is scalable on the large- scale 500k dataset.

Omni-Scale Feature Learning for Person Re-Identification

A novel deep ReID CNN is designed, termed Omni-Scale Network (OSNet), for omni-scale feature learning by designing a residual block composed of multiple convolutional feature streams, each detecting features at a certain scale.

Learning Discriminative Features with Multiple Granularities for Person Re-Identification

Comprehensive experiments implemented on the mainstream evaluation datasets including Market-1501, DukeMTMC-reid and CUHK03 indicate that the proposed end-to-end feature learning strategy robustly achieves state-of-the-art performances and outperforms any existing approaches by a large margin.