期刊
IEEE TRANSACTIONS ON IMAGE PROCESSING
卷 29, 期 -, 页码 7306-7316出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2020.3000904
关键词
Computer architecture; Semantics; Deep learning; Feature extraction; Visualization; Task analysis; Measurement; Person re-identification; pyramid representation; neural networks; deep learning
资金
- Horizon 2020 Research and Innovation Programme under the Marie Sklodowska-Curie [765866]
- Marie Curie Actions (MSCA) [765866] Funding Source: Marie Curie Actions (MSCA)
Learning discriminative, view-invariant and multi-scale representations of object appearance with different semantic levels is of paramount importance for person Re-Identification (ReID). Recently, the community has focused on learning deep Re-ID models to capture a single holistic representation. To improve the achieved results, additional visual attributes and object part-driven models have been considered, inevitably introducing additional human annotation labor or computational efforts. In this paper, we argue that pyramid-inspired methods capturing multi-scale information may overcome such requirements. Precisely, multi-scale pooled regions representing visual information of an object are integrated within a novel deep architecture factorizing them into discriminative features at multiple semantic levels. These are exploited through an attention mechanism later considered in an identification-similarity multi-task loss, trained by means of a curriculum learning strategy. Extensive results on three person ReID benchmarks demonstrate that better performance than existing methods are achieved. Code is available at https://github.com/iN1k1.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据