# OIMNet++: Prototypical Normalization and Localization-aware Learning for Person Search

arXiv: https://arxiv.org/abs/2207.10320 · HTML: https://mlsanity.com/paper/2207.10320/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 45 references that are in the map.
- First posted on arXiv 21 Jul 2022.

## Builds on (most cited first, 30 of 34)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [Deep Learning for Person Re-identification: A Survey and Outlook](https://mlsanity.com/paper/2001.04193/) (2020)
- [Bag of Tricks and A Strong Baseline for Deep Person Re-identification](https://mlsanity.com/paper/1903.07071/) (2019)
- [RMPE: Regional Multi-person Pose Estimation](https://mlsanity.com/paper/1612.00137/) (2016)
- [Omni-Scale Feature Learning for Person Re-Identification](https://mlsanity.com/paper/1905.00953/) (2019)
- [Joint Detection and Identification Feature Learning for Person Search](https://mlsanity.com/paper/1604.01850/) (2016)
- [Person Re-identification: Past, Present and Future](https://mlsanity.com/paper/1610.02984/) (2016)
- [Person Re-identification in the Wild](https://mlsanity.com/paper/1604.02531/) (2016)
- [Style Normalization and Restitution for Generalizable Person Re-identification](https://mlsanity.com/paper/2005.11037/) (2020)
- [Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models](https://mlsanity.com/paper/1702.03275/) (2017)
- [Fully Convolutional Instance-aware Semantic Segmentation](https://mlsanity.com/paper/1611.07709/) (2016)
- [Meta Batch-Instance Normalization for Generalizable Person Re-Identification](https://mlsanity.com/paper/2011.14670/) (2020)
- [Person Search via A Mask-Guided Two-Stream CNN Model](https://mlsanity.com/paper/1807.08107/) (2018)
- [Anchor-Free Person Search](https://mlsanity.com/paper/2103.11617/) (2021)
- [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)
- [Sequential End-to-end Network for Efficient Person Search](https://mlsanity.com/paper/2103.10148/) (2021)
- [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)

## Built on by (most cited first, 12 of 12)

- [Ground-to-Aerial Person Search: Benchmark Dataset and Approach](https://mlsanity.com/paper/2308.12712/) (2023)
- [Self-similarity Driven Scale-invariant Learning for Weakly Supervised Person Search](https://mlsanity.com/paper/2302.12986/) (2023)
- [Deep Intra-Image Contrastive Learning for Weakly Supervised One-Step Person Search](https://mlsanity.com/paper/2302.04607/) (2023)
- [PSDiff: Diffusion Model for Person Search with Iterative and Collaborative Refinement](https://mlsanity.com/paper/2309.11125/) (2023)
- [Domain Generalizable Person Search Using Unreal Dataset](https://mlsanity.com/paper/2404.00626/) (2024)
- [LEAPS: End-to-End One-Step Person Search With Learnable Proposals](https://mlsanity.com/paper/2303.11859/) (2023)
- [DDAM-PS: Diligent Domain Adaptive Mixer for Person Search](https://mlsanity.com/paper/2310.20706/) (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)
- [Generalizable Person Search on Open-world User-Generated Video Content](https://mlsanity.com/paper/2310.10068/) (2023)
- [Lifelong Person Search](https://mlsanity.com/paper/2407.21252/) (2024)
- [CLIPVehicle: A Unified Framework for Vision-based Vehicle Search](https://mlsanity.com/paper/2508.04120/) (2025)

## Abstract (arXiv)

We address the task of person search, that is, localizing and re-identifying query persons from a set of raw scene images. Recent approaches are typically built upon OIMNet, a pioneer work on person search, that learns joint person representations for performing both detection and person re-identification (reID) tasks. To obtain the representations, they extract features from pedestrian proposals, and then project them on a unit hypersphere with L2 normalization. These methods also incorporate all positive proposals, that sufficiently overlap with the ground truth, equally to learn person representations for reID. We have found that 1) the L2 normalization without considering feature distributions degenerates the discriminative power of person representations, and 2) positive proposals often also depict background clutter and person overlaps, which could encode noisy features to person representations. In this paper, we introduce OIMNet++ that addresses the aforementioned limitations. To this end, we introduce a novel normalization layer, dubbed ProtoNorm, that calibrates features from pedestrian proposals, while considering a long-tail distribution of person IDs, enabling L2 normalized person representations to be discriminative. We also propose a localization-aware feature learning scheme that encourages better-aligned proposals to contribute more in learning discriminative representations. Experimental results and analysis on standard person search benchmarks demonstrate the effectiveness of OIMNet++.