Aggregating Deep Pyramidal Representations for Person Re-Identification
Citations Over TimeTop 10% of 2019 papers
Abstract
Learning discriminative, view-invariant and multi-scale representations of person appearance with different semantic levels is of paramount importance for person Re-Identification (Re-ID). A surge of effort has been spent by the community to learn deep Re-ID models capturing a holistic single semantic level feature representation. To improve the achieved results, additional visual attributes and body part-driven models have been considered. However, these require extensive human annotation labor or demand additional computational efforts. We argue that a pyramid-inspired method capturing multi-scale information may overcome such requirements. Precisely, multi-scale stripes that represent visual information of a person can be used by a novel architecture factorizing them into latent discriminative factors at multiple semantic levels. A multi-task loss is combined with a curriculum learning strategy to learn a discriminative and invariant person representation which is exploited for triplet-similarity learning. Results on three benchmark Re-ID datasets demonstrate that better performance than existing methods are achieved (e.g., more than 90% accuracy on the Duke-MTMC dataset).
Related Papers
- Stable Discriminative Dictionary Learning Via Discriminative Deviation(2012)
- → Accurate And Fast Fine-Grained Image Classification via Discriminative Learning(2019)3 cited
- → Horizontal Pyramid Matching for Person Re-identification(2018)59 cited
- → MixSiam: A Mixture-based Approach to Self-supervised Representation Learning(2021)8 cited
- → Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedback(2023)