# Mitigate Domain Shift by Primary-Auxiliary Objectives Association for Generalizing Person ReID

arXiv: https://arxiv.org/abs/2310.15913 · HTML: https://mlsanity.com/paper/2310.15913/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 50 references that are in the map.
- First posted on arXiv 24 Oct 2023.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [A Survey on Multi-Task Learning](https://mlsanity.com/paper/1707.08114/) (2017)
- [Multi-Task Learning as Multi-Objective Optimization](https://mlsanity.com/paper/1810.04650/) (2018)
- [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022)
- [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017)
- [Learning to Generate Novel Domains for Domain Generalization](https://mlsanity.com/paper/2007.03304/) (2020)
- [Domain Generalization using Causal Matching](https://mlsanity.com/paper/2006.07500/) (2020)
- [Joint Discriminative and Generative Learning for Person Re-identification](https://mlsanity.com/paper/1904.07223/) (2019)
- [Harmonious Attention Network for Person Re-Identification](https://mlsanity.com/paper/1802.08122/) (2018)
- [Style Normalization and Restitution for Generalizable Person Re-identification](https://mlsanity.com/paper/2005.11037/) (2020)
- [Pyramid Feature Attention Network for Saliency detection](https://mlsanity.com/paper/1903.00179/) (2019)
- [Relation-Aware Global Attention for Person Re-identification](https://mlsanity.com/paper/1904.02998/) (2019)
- [Identity-Guided Human Semantic Parsing for Person Re-Identification](https://mlsanity.com/paper/2007.13467/) (2020)
- [Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification](https://mlsanity.com/paper/2012.00417/) (2020)
- [Salient Object Detection: A Survey](https://mlsanity.com/paper/1411.5878/) (2014)
- [Meta Batch-Instance Normalization for Generalizable Person Re-Identification](https://mlsanity.com/paper/2011.14670/) (2020)
- [Generalizable Person Re-identification with Relevance-aware Mixture of Experts](https://mlsanity.com/paper/2105.09156/) (2021)
- [Tent: Fully Test-time Adaptation by Entropy Minimization](https://mlsanity.com/paper/2006.10726/) (2020)
- [Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restoration](https://mlsanity.com/paper/2107.05446/) (2021)
- [Frustratingly Easy Person Re-Identification: Generalizing Person Re-ID in Practice](https://mlsanity.com/paper/1905.03422/) (2019)
- [Feature Alignment and Restoration for Domain Generalization and Adaptation](https://mlsanity.com/paper/2006.12009/) (2020)
- [Mimic Embedding via Adaptive Aggregation: Learning Generalizable Person Re-identification](https://mlsanity.com/paper/2112.08684/) (2021)
- [Generalizable Person Re-Identification via Self-Supervised Batch Norm Test-Time Adaption](https://mlsanity.com/paper/2203.00672/) (2022)
- [DEX: Domain Embedding Expansion for Generalized Person Re-identification](https://mlsanity.com/paper/2110.11391/) (2021)
- [Local-Global Associative Frame Assemble in Video Re-ID](https://mlsanity.com/paper/2110.12018/) (2021)

## Built on by (most cited first, 3 of 3)

- [Beyond Role-Based Surgical Domain Modeling: Generalizable Re-Identification in the Operating Room](https://mlsanity.com/paper/2503.13028/) (2025)
- [CORE-ReID: Comprehensive Optimization and Refinement through Ensemble fusion in Domain Adaptation for person re-identification](https://mlsanity.com/paper/2508.03064/) (2025)
- [CORE-ReID V2: Advancing the Domain Adaptation for Object Re-Identification with Optimized Training and Ensemble Fusion](https://mlsanity.com/paper/2508.04036/) (2025)

## Abstract (arXiv)

While deep learning has significantly improved ReID model accuracy under the independent and identical distribution (IID) assumption, it has also become clear that such models degrade notably when applied to an unseen novel domain due to unpredictable/unknown domain shift. Contemporary domain generalization (DG) ReID models struggle in learning domain-invariant representation solely through training on an instance classification objective. We consider that a deep learning model is heavily influenced and therefore biased towards domain-specific characteristics, e.g., background clutter, scale and viewpoint variations, limiting the generalizability of the learned model, and hypothesize that the pedestrians are domain invariant owning they share the same structural characteristics. To enable the ReID model to be less domain-specific from these pure pedestrians, we introduce a method that guides model learning of the primary ReID instance classification objective by a concurrent auxiliary learning objective on weakly labeled pedestrian saliency detection. To solve the problem of conflicting optimization criteria in the model parameter space between the two learning objectives, we introduce a Primary-Auxiliary Objectives Association (PAOA) mechanism to calibrate the loss gradients of the auxiliary task towards the primary learning task gradients. Benefiting from the harmonious multitask learning design, our model can be extended with the recent test-time diagram to form the PAOA+, which performs on-the-fly optimization against the auxiliary objective in order to maximize the model's generative capacity in the test target domain. Experiments demonstrate the superiority of the proposed PAOA model.