Camera Alignment and Weighted Contrastive Learning for Domain Adaptation in Video Person ReID

Mekhazni, Djebril; Dufau, Maximilien; Desrosiers, Christian; Pedersoli, Marco; Granger, Éric

doi:10.1109/wacv56688.2023.00167

Cited by 5 publications

(2 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pixel-wise contrastive learning improves the robustness and quality of feature representation by increasing the discrimination between positive and negative samples and decreasing the distance within pairs of positive or negative samples [45][46][47]. However, the independent pixel-wise features ignore the building's global consistency representations such as structure and texture.…”

Section: Instance-level Constraint Contrastive Lossmentioning

confidence: 99%

Multilevel Feature Aggregated Network with Instance Contrastive Learning Constraint for Building Extraction

Li,

Bao,

Liu

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Building footprint extraction from remotely sensed imagery is a critical task in the field of illegal building discovery, urban dynamic monitoring, and disaster emergency response. Recent research has made significant progress in this area by utilizing deep learning techniques. However, it remains difficult to efficiently balance the spatial detail and rich semantic features. In particular, the extracted building edge is often inaccurate, especially in areas where the buildings are densely distributed, and the boundary of adjacent building instances is difficult to distinguish accurately. Additionally, identifying buildings with varying scales remains a challenging problem. To address the above problems, we designed a novel framework that aggregated multilevel contextual information extracted from multiple encoders. Furthermore, we introduced an instance constraint into contrastive learning to enhance the robustness of the feature representation. Experimental results demonstrated that our proposed method achieved 91.07% and 74.58% on the intersection over union metric on the WHU and Massachusetts datasets, respectively, outperforming the most recent related methods. Notably, our method significantly improved the accuracy of building boundaries, especially at the building instance level, and the integrity of multi-scale buildings.

show abstract

Section: Instance-level Constraint Contrastive Lossmentioning

confidence: 99%

Multilevel Feature Aggregated Network with Instance Contrastive Learning Constraint for Building Extraction

Li,

Bao,

Liu

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Recently, research on unsupervised learning has become increasingly important due to the high cost of labeling large-scale datasets in supervised learning. As an important branch of unsupervised learning, clustering can group similar samples according to their underlying distribution without any labels; as a result, it has become increasingly crucial in many applications, such as facial expression recognition [1], video action recognition [2], recommendation systems [3], and domain adaptation [4][5][6] due to its good hidden correlation exploiting capability.…”

Section: Introductionmentioning

confidence: 99%

Deep Clustering by Graph Attention Contrastive Learning

Lei

Liu

et al. 2023

Electronics

View full text Add to dashboard Cite

Contrastive learning shows great potential in deep clustering. It uses constructed pairs to discover the feature distribution that is required for the clustering task. In addition to conventional augmented pairs, recent methods have introduced more methods of creating highly confident pairs, such as nearest neighbors, to provide more semantic prior knowledge. However, existing works only use partial pairwise similarities to construct semantic pairs locally without capturing the entire sample’s relationships from a global perspective. In this paper, we propose a novel clustering framework called graph attention contrastive learning (GACL) to aggregate more semantic information. To this end, GACL is designed to simultaneously perform instance-level and graph-level contrast. Specifically, with its novel graph attention mechanism, our model explores more undiscovered pairs and selectively focuses on informative pairs. To ensure local and global clustering consistency, we jointly use the designed graph-level and instance-level contrastive losses. Experiments on six challenging image benchmarks demonstrate the superiority of our proposed approach over state-of-the-art methods.

show abstract

Situational diversity in video person re-identification: introducing MSA-BUPT dataset

Zhao,

Liu,

Zhao

et al. 2024

Complex Intell. Syst.

View full text Add to dashboard Cite

Thanks to the success of deep learning over the past few years, the video person re-identification (ReID) algorithms have achieved high accuracy on multiple public benchmark datasets. However, the available video person ReID datasets cover a limited range of real-world scenarios, and they have several obvious limitations: limited camera viewing angles, tiny variations of the shooting scene, and even errors in manual labels. These disadvantages prevent video person ReID from being widely used in real-life scenarios. In this work, a new high-quality multi-situation video person ReID dataset, named MSA-BUPT, is built to promote the video person ReID task in large-scale urban surveillance. Specifically, MSA-BUPT contains 684 identities, 2,665 trajectories, and nearly 250,000 frames from 200-h videos across various complex scenarios. Person attribute annotations and unannotated video data are also provided for other research perspectives, such as cross-modality ReID, cross-domain ReID, and so on. Furthermore, two plug-and-play components are used to improve retrieval capabilities: a new scenario-based data augmentation method is proposed to alleviate the person misalignment problem; a re-ranking strategy based on person attribute is applied to make secondary adjustments to the content to the results of the model. The extensive experimental results show that the above methods improve the performance of some representative state-of-the-art models on the new dataset.

show abstract

Camera Alignment and Weighted Contrastive Learning for Domain Adaptation in Video Person ReID

Cited by 5 publications

References 34 publications

Multilevel Feature Aggregated Network with Instance Contrastive Learning Constraint for Building Extraction

Multilevel Feature Aggregated Network with Instance Contrastive Learning Constraint for Building Extraction

Deep Clustering by Graph Attention Contrastive Learning

Situational diversity in video person re-identification: introducing MSA-BUPT dataset

Contact Info

Product

Resources

About