Relation Network for Person Re-Identification

Abstract

Person re-identification (reID) aims at retrieving an image of the person of interest from a set of images typically captured by multiple cameras. Recent reID methods have shown that exploiting local features describing body parts, together with a global feature of a person image itself, gives robust feature representations, even in the case of missing body parts. However, using the individual part-level features directly, without considering relations between body parts, confuses differentiating identities of different persons having similar attributes in corresponding parts. To address this issue, we propose a new relation network for person reID that considers relations between individual body parts and the rest of them. Our model makes a single part-level feature incorporate partial information of other body parts as well, supporting it to be more discriminative. We also introduce a global contrastive pooling (GCP) method to obtain a global feature of a person image. We propose to use contrastive features for GCP to complement conventional max and averaging pooling techniques. We show that our model outperforms the state of the art on the Market1501, DukeMTMC-reID and CUHK03 datasets, demonstrating the effectiveness of our approach on discriminative person representations.

Exploiting robust unsupervised video person re‐identification

“…In the first part of proposed scheme, that is, feature extraction , CNN is employed to extract an initial feature map $$f$$ with a size of $$h \times w \times c$$ ($$h, w, c$$ are height, width, and the number of channels, respectively) from a person image. In the second part, that is, local/global‐aware feature generation , feature map $$f$$ is divided equally into $$k$$ horizontal stripes, which follows the operations in references [20, 29, 48]. Each stripe has a smaller receptive field than the global‐level feature $$f$$.…”

Noise Resistible Network for Unsupervised Domain Adaptation on Person Re-Identification

“…Also, Huang et al [25] propose 3-Dimension Transmissible Attention (3DTA) that cooperatively utilizes channel attention and spatial attention, with a group loss to optimize the feature distances. In [31], relation network puts forward a global attention mechanism with relation-aware and has achieved superior performance. Zhang et al [32] focus on different attributes of a person including sex, hair, etc.…”

Deep Camera‐Aware Metric Learning for Person Reidentification

“…For example, semantic feature learning is studied via multistage ROI pooling in the work [1]. In the work [2], relations among individual body parts are explored through a GCP network. Additionally, metric learning aims to map semantically similar persons from some manifold onto metrically close person points in another space.…”

“…(1) We propose a deep camera-aware metric learning (DCAML) model to discover the relationship between camera and identity, where camera-level and identity-level information jointly contribute to the retrieval accuracy (2) We develop a dynamic training strategy to integrate multiple metrics as a unified optimization objective…”