# Decoupled and Memory-Reinforced Networks: Towards Effective Feature Learning for One-Step Person Search

arXiv: https://arxiv.org/abs/2102.10795 · HTML: https://mlsanity.com/paper/2102.10795/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 32 references that are in the map.
- First posted on arXiv 22 Feb 2021.

## Builds on (most cited first, 25 of 25)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results](https://mlsanity.com/paper/1703.01780/) (2017)
- [R-FCN: Object Detection via Region-based Fully Convolutional Networks](https://mlsanity.com/paper/1605.06409/) (2016)
- [Circle Loss: A Unified Perspective of Pair Similarity Optimization](https://mlsanity.com/paper/2002.10857/) (2020)
- [RepPoints: Point Set Representation for Object Detection](https://mlsanity.com/paper/1904.11490/) (2019)
- [Joint Detection and Identification Feature Learning for Person Search](https://mlsanity.com/paper/1604.01850/) (2016)
- [Person Re-identification in the Wild](https://mlsanity.com/paper/1604.02531/) (2016)
- [Learning Context Graph for Person Search](https://mlsanity.com/paper/1904.01830/) (2019)
- [Person Search via A Mask-Guided Two-Stream CNN Model](https://mlsanity.com/paper/1807.08107/) (2018)
- [Re-ID Driven Localization Refinement for Person Search](https://mlsanity.com/paper/1909.08580/) (2019)
- [Query-guided End-to-End Person Search](https://mlsanity.com/paper/1905.01203/) (2019)
- [Person Search by Multi-Scale Matching](https://mlsanity.com/paper/1807.08582/) (2018)
- [Neural Person Search Machines](https://mlsanity.com/paper/1707.06777/) (2017)
- [Robust Partial Matching for Person Search in the Wild](https://mlsanity.com/paper/2004.09329/) (2020)
- [IAN: The Individual Aggregation Network for Person Search](https://mlsanity.com/paper/1705.05552/) (2017)
- [Tasks Integrated Networks: Joint Detection and Retrieval for Image Search](https://mlsanity.com/paper/2009.01438/) (2020)

## Built on by (most cited first, 19 of 19)

- [Cascade Transformers for End-to-End Person Search](https://mlsanity.com/paper/2203.09642/) (2022)
- [PSTR: End-to-End One-Step Person Search With Transformers](https://mlsanity.com/paper/2204.03340/) (2022)
- [Weakly Supervised Person Search with Region Siamese Networks](https://mlsanity.com/paper/2109.06109/) (2021)
- [Ground-to-Aerial Person Search: Benchmark Dataset and Approach](https://mlsanity.com/paper/2308.12712/) (2023)
- [Gallery Filter Network for Person Search](https://mlsanity.com/paper/2210.12903/) (2022)
- [Self-similarity Driven Scale-invariant Learning for Weakly Supervised Person Search](https://mlsanity.com/paper/2302.12986/) (2023)
- [Context-Aware Unsupervised Clustering for Person Search](https://mlsanity.com/paper/2110.01341/) (2021)
- [Deep Intra-Image Contrastive Learning for Weakly Supervised One-Step Person Search](https://mlsanity.com/paper/2302.04607/) (2023)
- [Making Person Search Enjoy the Merits of Person Re-identification](https://mlsanity.com/paper/2108.10536/) (2021)
- [Query-Guided Networks for Few-shot Fine-grained Classification and Person Search](https://mlsanity.com/paper/2209.10250/) (2022)
- [PSDiff: Diffusion Model for Person Search with Iterative and Collaborative Refinement](https://mlsanity.com/paper/2309.11125/) (2023)
- [Prompting Continual Person Search](https://mlsanity.com/paper/2410.19239/) (2024)
- [Learning Context-Aware Embedding for Person Search](https://mlsanity.com/paper/2111.14316/) (2021)
- [PS-ARM: An End-to-End Attention-aware Relation Mixer Network for Person Search](https://mlsanity.com/paper/2210.03433/) (2022)
- [Sequential Transformer for End-to-End Person Search](https://mlsanity.com/paper/2211.04323/) (2022)
- [LEAPS: End-to-End One-Step Person Search With Learnable Proposals](https://mlsanity.com/paper/2303.11859/) (2023)
- [Leveraging Prior Knowledge of Diffusion Model for Person Search](https://mlsanity.com/paper/2510.01841/) (2025)
- [Towards Fully Decoupled End-to-End Person Search](https://mlsanity.com/paper/2309.04967/) (2023)
- [ICON: Invariant Counterfactual Optimization with Neuro-Symbolic Priors for Text-Based Person Search](https://mlsanity.com/paper/2601.15931/) (2026)

## Abstract (arXiv)

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 similarity pair construction for pairwise metric learning. For better encoding consistency of the stored features, a slow-moving average of the network is applied for extracting these features. In this way, the dual networks reinforce each other and converge to robust solution states. Experimentally, the proposed method obtains 93.2% and 46.9% mAP on CUHK-SYSU and PRW datasets, which exceeds all the existing one-step methods.