Decoupled And Memory-reinforced Networks: Towards Effective Feature Learning For One-step Person Search

Abstract

The goal of person search is to localize and match query persons from scene images. For high efficiency, one-step methods have been developed to jointly handle the pedestrian detection and identification sub-tasks using a single network. There are two major challenges in the current one-step approaches. One is the mutual interference between the optimization objectives of multiple sub-tasks. The other is the sub-optimal identification feature learning caused by small batch size when end-to-end training. To overcome these problems, we propose a decoupled and memory-reinforced network (DMRNet). Specifically, to reconcile the conflicts of multiple objectives, we simplify the standard tightly coupled pipelines and establish a deeply decoupled multi-task learning framework. Further, we build a memory-reinforced mechanism to boost the identification feature learning. By queuing the identification features of recently accessed instances into a memory bank, the mechanism augments the similarit

Stats

• citations42
• S2 citations—
• github stars0
• HF likes0
• heat score12.25
• arxiv keyhan2021decoupled

Related papers

• Multi-attribute Enhancement Network For Person Search (2021)7.84
• Deep-person: Learning Discriminative Deep Features For Person Re-identification (2017)16.90
• Learning Context-aware Embedding For Person Search (2021)0.00
• Neighbor-based Feature And Index Enhancement For Person Re-identification (2025)0.00
• Ranking And Classification Driven Feature Learning For Person Re_identification (2019)4.01
• Maskreid: A Mask Based Deep Ranking Neural Network For Person Re-identification (2018)0.00
• Structured Deep Hashing With Convolutional Neural Networks For Fast Person Re-identification (2017)12.87
• Pedestrian Alignment Network For Large-scale Person Re-identification (2017)18.71