MagnifierNet: Towards Semantic Regularization and Fusion for Person Re-identification

by   Yushi Lan, et al.

Although person re-identification (ReID) has achieved significant improvement recently by enforcing part alignment, it is still a challenging task when it comes to distinguishing visually similar identities or identifying occluded person. In these scenarios, magnifying details in each part features and selectively fusing them together may provide a feasible solution. In this paper, we propose MagnifierNet, a novel network which accurately mines details for each semantic region and selectively fuse all semantic feature representations. Apart from conventional global branch, our proposed network is composed of a Semantic Regularization Branch (SRB) as learning regularizer and a Semantic Fusion Branch (SFB) towards selectively semantic fusion. The SRB learns with limited number of semantic regions randomly sampled in each batch, which forces the network to learn detailed representation for each semantic region, and the SFB selectively fuses semantic region information in a sequential manner, focusing on beneficial information while neglecting irrelevant features or noises. In addition, we introduce a novel loss function "Semantic Diversity Loss" (SD Loss) to facilitate feature diversity and improves regularization among all semantic regions. State-of-the-art performance has been achieved on multiple datasets by large margins. Notably, we improve SOTA on CUHK03-Labeled Dataset by 12.6 We also outperform existing works on CUHK03-Detected Dataset by 13.2 and 7.8 method.


page 1

page 3

page 4

page 5


Batch Feature Erasing for Person Re-identification and Beyond

This paper presents a new training mechanism called Batch Feature Erasin...

Diversity-Achieving Slow-DropBlock Network for Person Re-Identification

A big challenge of person re-identification (Re-ID) using a multi-branch...

Learning Discriminative Features with Multiple Granularities for Person Re-Identification

The combination of global and partial features has been an essential sol...

Ranking and Classification driven Feature Learning for Person Re_identification

Person re-identification has attracted many researchers' attention for i...

Unified Multifaceted Feature Learning for Person Re-Identification

Person re-identification (ReID) aims at re-identifying persons from diff...

Rethinking Temporal Fusion for Video-based Person Re-identification on Semantic and Time Aspect

Recently, the research interest of person re-identification (ReID) has g...

Receptive Multi-granularity Representation for Person Re-Identification

A key for person re-identification is achieving consistent local details...

Please sign up or login with your details

Forgot password? Click here to reset