Cross-entropy Adversarial View Adaptation For Person Re-identification
2019 · Lin Wu, Richang Hong, Yang Wang, et al.
Abstract
Person re-identification (re-ID) is a task of matching pedestrians under disjoint camera views. To recognise paired snapshots, it has to cope with large cross-view variations caused by the camera view shift. Supervised deep neural networks are effective in producing a set of non-linear projections that can transform cross-view images into a common feature space. However, they typically impose a symmetric architecture, yielding the network ill-conditioned on its optimisation. In this paper, we learn view-invariant subspace for person re-ID, and its corresponding similarity metric using an adversarial view adaptation approach. The main contribution is to learn coupled asymmetric mappings regarding view characteristics which are adversarially trained to address the view discrepancy by optimising the cross-entropy view confusion objective. To determine the similarity value, the network is empowered with a similarity discriminator to promote features that are highly discriminant in distingu
Authors
(none)
Tags
Stats
Related papers
- Cross-view Kernel Similarity Metric Learning Using Pairwise Constraints For Person Re-identification (2019)0.00
- A Pose-sensitive Embedding For Person Re-identification With Expanded Cross Neighborhood Re-ranking (2017)23.25
- A Discriminatively Learned CNN Embedding For Person Re-identification (2016)20.32
- Interpretable And Generalizable Person Re-identification With Query-adaptive Convolution And Temporal Lifting (2019)20.43
- Deep Co-attention Based Comparators For Relative Representation Learning In Person Re-identification (2018)13.34
- Multi-expert Adversarial Attack Detection In Person Re-identification Using Context Inconsistency (2021)11.67
- Fully Unsupervised Person Re-identification Viaselective Contrastive Learning (2020)9.92
- Advancing Person Re-identification: Tensor-based Feature Fusion And Multilinear Subspace Learning (2023)2.26