Calibrated Domain-Invariant Learning for Highly Generalizable Large Scale Re-Identification

by   Wuyang Chen, et al.

Many real-world applications, such as city-scale traffic monitoring and control, requires large-scale re-identification. However, previous ReID methods often failed to address two limitations in existing ReID benchmarks, i.e., low spatiotemporal coverage and sample imbalance. Notwithstanding their demonstrated success in every single benchmark, they have difficulties in generalizing to unseen environments. As a result, these methods are less applicable in a large-scale setting due to poor generalization. In seek for a highly generalizable large-scale ReID method, we present an adversarial domain invariant feature learning framework (ADIN) that explicitly learns to separate identity-related features from challenging variations, where for the first time "free" annotations in ReID data such as video timestamp and camera index are utilized. Furthermore, we find that the imbalance of nuisance classes jeopardizes the adversarial training, and for mitigation we propose a calibrated adversarial loss that is attentive to nuisance distribution. Experiments on existing large-scale person vehicle ReID datasets demonstrate that ADIN learns more robust and generalizable representations, as evidenced by its outstanding direct transfer performance across datasets, which is a criterion that can better measure the generalizability of large-scale ReID methods/


DomainMix: Learning Generalizable Person Re-Identification Without Human Annotations

Existing person re-identification methods often have low generalization ...

Hierarchical Invariant Feature Learning with Marginalization for Person Re-Identification

This paper addresses the problem of matching pedestrians across multiple...

Learning Domain Invariant Representations for Generalizable Person Re-Identification

Generalizable person Re-Identification (ReID) has attracted growing atte...

Self-paced Ensemble for Highly Imbalanced Massive Data Classification

Many real-world applications reveal difficulties in learning classifiers...

Adversarial Pairwise Reverse Attention for Camera Performance Imbalance in Person Re-identification: New Dataset and Metrics

Existing evaluation metrics for Person Re-Identification (Person ReID) m...

Diverse Large-Scale ITS Dataset Created from Continuous Learning for Real-Time Vehicle Detection

In traffic engineering, vehicle detectors are trained on limited dataset...

LARD: Large-scale Artificial Disfluency Generation

Disfluency detection is a critical task in real-time dialogue systems. H...