Search Results for author:
Found 5 papers, 2 papers with code
Is Synthetic Dataset Reliable for Benchmarking Generalizable Person Re-Identification?
Through the designed pairwise ranking analysis and comprehensive evaluations, we conclude that a recent large-scale synthetic dataset ClonedPerson can be reliably used to benchmark GPReID, statistically the same as real-world datasets.
Ranked #1 on
Generalizable Person Re-identification
on ClonedPerson
(using extra training data)
Dynamically Decoding Source Domain Knowledge for Domain Generalization
Thus, source domain knowledge gets dynamically decoded for inference of the current input from unseen domain.
Discovering Spatial Relationships by Transformers for Domain Generalization
However, though CNNs have a strong ability to find the discriminative features, they do a poor job of modeling the relations between different locations in the image due to the response to CNN filters are mostly local.
DomainMix: Learning Generalizable Person Re-Identification Without Human Annotations
In this way, human annotations are no longer required, and it is scalable to large and diverse real-world datasets.
Generalizable Person Re-identification
Unsupervised Domain Adaptation
Cross-Modal Similarity Learning : A Low Rank Bilinear Formulation
A new approach to the problem has been raised which intends to match features of different modalities directly.
