Progressive Learning Algorithm for Efficient Person Re-Identification
This addresses efficiency issues in ReID for large-scale applications, offering a more practical solution, though it appears incremental as it builds on existing loss functions.
The paper tackles the problem of high computational cost and memory consumption in Person Re-Identification (ReID) for large-scale applications by developing a Progressive Learning Algorithm (PLA) that enhances triplet and cross-entropy losses, achieving Rank-1=94.7% and mAP=89.4% on Market-1501 while saving at least 30% parameters compared to strong part models.
This paper studies the problem of Person Re-Identification (ReID)for large-scale applications. Recent research efforts have been devoted to building complicated part models, which introduce considerably high computational cost and memory consumption, inhibiting its practicability in large-scale applications. This paper aims to develop a novel learning strategy to find efficient feature embeddings while maintaining the balance of accuracy and model complexity. More specifically, we find by enhancing the classical triplet loss together with cross-entropy loss, our method can explore the hard examples and build a discriminant feature embedding yet compact enough for large-scale applications. Our method is carried out progressively using Bayesian optimization, and we call it the Progressive Learning Algorithm (PLA). Extensive experiments on three large-scale datasets show that our PLA is comparable or better than the-state-of-the-arts. Especially, on the challenging Market-1501 dataset, we achieve Rank-1=94.7\%/mAP=89.4\% while saving at least 30\% parameters than strong part models.