Abstract
As an instance-level recognition problem, person re-identification (ReID) relies on discriminative features, which not only capture different spatial scales but also encapsulate an arbitrary combination of multiple scales. We call these features of both homogeneous and heterogeneous scales omni-scale features. In this paper, a novel deep CNN is designed, termed Omni-Scale Network (OSNet), for omni-scale feature learning in ReID. This is achieved by designing a residual block composed of multiple convolutional feature streams, each detecting features at a certain scale. Importantly, a novel unified aggregation gate is introduced to dynamically fuse multi-scale features with input-dependent channel-wise weights. To efficiently learn spatial-channel correlations and avoid overfitting, the building block uses both pointwise and depthwise convolutions. By stacking such blocks layer-by-layer, our OSNet is extremely lightweight and can be trained from scratch on existing ReID benchmarks. Despite its small model size, our OSNet achieves state-of-the-art performance on six person-ReID datasets.
Abstract (translated)
作为一个实例级的识别问题,人的再识别(REID)依赖于识别特征,它不仅捕获了不同的空间尺度,而且还封装了多尺度的任意组合。我们称这些特征为同质和异质尺度的全尺度特征。本文设计了一种全新的深度CNN,称为OSNET,用于REID中的全尺度特征学习。这是通过设计一个由多个卷积特征流组成的剩余块来实现的,每个卷积特征流在一定的尺度上检测特征。重要的是,引入了一种新的统一聚合门来动态融合具有输入相关信道权重的多尺度特征。为了有效地学习空间信道相关性并避免过度拟合,构建块同时使用点向和非方向卷积。通过一层一层地堆叠这些块,我们的OSnet非常轻,可以在现有REID基准上从头开始训练。尽管型号较小,我们的OSNET在六个人的REID数据集上仍取得了最先进的性能。
URL
https://arxiv.org/abs/1905.00953