Illumination Adaptive Person Reid Based on Teacher-Student Model and Adversarial Training

Zhang, Ziyue; Xu, Richard Yi Da; Jiang, Shuai; Li, Yang; Huang, Congzhentao; Deng, Changhong

doi:10.1109/icip40778.2020.9190796

Cited by 11 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zeng et al [30] proposed an illumination identity disentanglement (IID) network to dispel different scales of illumination away while maintaining each identity's discriminant information. Zhang et al [31] proposed using an illumination teacher model trained by the differences between the illumination-adjusted and original images to separate the ReID features from lighting features to enhance ReID performance. Although low illumination promotes vehicle ReID, extremely unsatisfactory illumination conditions are still killers of vehicle ReID.…”

Section: Visible Re-identificationmentioning

confidence: 99%

Progressively Hybrid Transformer for Multi-Modal Vehicle Re-Identification

Pan

Huang

Liang

et al. 2023

Sensors

View full text Add to dashboard Cite

Multi-modal (i.e., visible, near-infrared, and thermal-infrared) vehicle re-identification has good potential to search vehicles of interest in low illumination. However, due to the fact that different modalities have varying imaging characteristics, a proper multi-modal complementary information fusion is crucial to multi-modal vehicle re-identification. For that, this paper proposes a progressively hybrid transformer (PHT). The PHT method consists of two aspects: random hybrid augmentation (RHA) and a feature hybrid mechanism (FHM). Regarding RHA, an image random cropper and a local region hybrider are designed. The image random cropper simultaneously crops multi-modal images of random positions, random numbers, random sizes, and random aspect ratios to generate local regions. The local region hybrider fuses the cropped regions to let regions of each modal bring local structural characteristics of all modalities, mitigating modal differences at the beginning of feature learning. Regarding the FHM, a modal-specific controller and a modal information embedding are designed to effectively fuse multi-modal information at the feature level. Experimental results show the proposed method wins the state-of-the-art method by a larger 2.7% mAP on RGBNT100 and a larger 6.6% mAP on RGBN300, demonstrating that the proposed method can learn multi-modal complementary information effectively.

show abstract

Section: Visible Re-identificationmentioning

confidence: 99%

Progressively Hybrid Transformer for Multi-Modal Vehicle Re-Identification

Pan

Huang

Liang

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Recently, person re-ID has attracted attention from both the community and the industry due to its practical value in public safety and private property security. With the development of deep neural networks [4], great progress has been made in person re-ID and most of the existing studies focus on challenges from camera settings [5][6][7], occlusions [8,9], viewpoints [10][11][12], illumination-adaptive [13][14][15], modalities [16][17][18] and cloth-changing [19,20]. Although these methods have achieved inspiring matching accuracy on public benchmarks [21,22], they have a common limitation in that they are designed based on a prerequisite that the images captured by different cameras are of the same resolution.…”

Section: Introductionmentioning

confidence: 99%

Multi-Scale Image- and Feature-Level Alignment for Cross-Resolution Person Re-Identification

Zhang,

Wang,

Zhang

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Cross-Resolution Person Re-Identification (re-ID) aims to match images with disparate resolutions arising from variations in camera hardware and shooting distances. Most conventional works utilize Super-Resolution (SR) models to recover Low Resolution (LR) images to High Resolution (HR) images. However, because the SR models cannot completely compensate for the missing information in the LR images, there is still a large gap between the HR image recovered from the LR images and the real HR images. To tackle this challenge, we propose a novel Multi-Scale Image- and Feature-Level Alignment (MSIFLA) framework to align the images on multiple resolution scales at both the image and feature level. Specifically, (i) we design a Cascaded Multi-Scale Resolution Reconstruction (CMSR2) module, which is composed of three cascaded Image Reconstruction (IR) networks, and can continuously reconstruct multiple variables of different resolution scales from low to high for each image, regardless of image resolution. The reconstructed images with specific resolution scales are of similar distribution; therefore, the images are aligned on multiple resolution scales at the image level. (ii) We propose a Multi-Resolution Representation Learning (MR2L) module which consists of three-person re-ID networks to encourage the IR models to preserve the ID-discriminative information during training separately. Each re-ID network focuses on mining discriminative information from a specific scale without the disturbance from various resolutions. By matching the extracted features on three resolution scales, the images with different resolutions are also aligned at the feature-level. We conduct extensive experiments on multiple public cross-resolution person re-ID datasets to demonstrate the superiority of the proposed method. In addition, the generalization of MSIFLA in handling cross-resolution retrieval tasks is verified on the UAV vehicle dataset.

show abstract

“…Due to the success of convolutional neural networks (CNNs), a variety of learning-based methods [3,4,5] have been proposed to address person ReID problem and achieved good performance on many benchmarks. Nevertheless, with the presence of people occlusions [6,7], viewpoint changes [5,8], pose changes [9,10], and even illumination changes [11,12], person reID remains a very challenging task.…”

Section: Introductionmentioning

confidence: 99%

Resolution-Invariant Person Reid Based On Feature Transformation And Self-Weighted Attention

Zhang

Jiang

Huang

et al. 2021

2021 IEEE International Conference on Image Processing (ICIP)

Self Cite

View full text Add to dashboard Cite

Person Re-identification (ReID) is a critical computer vision task which aims to match the same person in images or video sequences. Most current works focus on settings where the resolution of images is kept the same. However, the resolution is a crucial factor in person ReID, especially when the cameras are at different distances from the person or the camera's models are different from each other. In this paper, we propose a novel two-stream network with a lightweight resolution association ReID feature transformation (RAFT) module and a self-weighted attention (SWA) ReID module to evaluate features under different resolutions. RAFT transforms the low resolution features to corresponding high resolution features. SWA evaluates both features to get weight factors for the person ReID. Both modules are jointly trained to get a resolution-invariant representation. Extensive experiments on five benchmark datasets show the effectiveness of our method. For instance, we achieve Rank-1 accuracy of 43.3% and 83.2% on CAVIAR and MLR-CUHK03, outperforming the state-of-the-art.

show abstract

Illumination Adaptive Person Reid Based on Teacher-Student Model and Adversarial Training

Cited by 11 publications

References 17 publications

Progressively Hybrid Transformer for Multi-Modal Vehicle Re-Identification

Progressively Hybrid Transformer for Multi-Modal Vehicle Re-Identification

Multi-Scale Image- and Feature-Level Alignment for Cross-Resolution Person Re-Identification

Resolution-Invariant Person Reid Based On Feature Transformation And Self-Weighted Attention

Contact Info

Product

Resources

About