# Learning to Balance: Diverse Normalization for Cloth-Changing Person Re-Identification

arXiv: https://arxiv.org/abs/2410.03977 · HTML: https://mlsanity.com/paper/2410.03977/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 48 references that are in the map.
- First posted on arXiv 4 Oct 2024.

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

- [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)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)](https://mlsanity.com/paper/1711.09349/) (2017)
- [TransReID: Transformer-based Object Re-Identification](https://mlsanity.com/paper/2102.04378/) (2021)
- [Bag of Tricks and A Strong Baseline for Deep Person Re-identification](https://mlsanity.com/paper/1903.07071/) (2019)
- [Environment Inference for Invariant Learning](https://mlsanity.com/paper/2010.07249/) (2020)
- [Omni-Scale Feature Learning for Person Re-Identification](https://mlsanity.com/paper/1905.00953/) (2019)
- [Learning Discriminative Features with Multiple Granularities for Person Re-Identification](https://mlsanity.com/paper/1804.01438/) (2018)
- [Concept Whitening for Interpretable Image Recognition](https://mlsanity.com/paper/2002.01650/) (2020)
- [Joint Discriminative and Generative Learning for Person Re-identification](https://mlsanity.com/paper/1904.07223/) (2019)
- [Cheap Orthogonal Constraints in Neural Networks: A Simple Parametrization of the Orthogonal and Unitary Group](https://mlsanity.com/paper/1901.08428/) (2019)
- [Clothes-Changing Person Re-identification with RGB Modality Only](https://mlsanity.com/paper/2204.06890/) (2022)
- [Full-Capacity Unitary Recurrent Neural Networks](https://mlsanity.com/paper/1611.00035/) (2016)
- [Orthogonal Weight Normalization: Solution to Optimization over Multiple Dependent Stiefel Manifolds in Deep Neural Networks](https://mlsanity.com/paper/1709.06079/) (2017)
- [Iterative Normalization: Beyond Standardization towards Efficient Whitening](https://mlsanity.com/paper/1904.03441/) (2019)
- [Person Re-identification by Contour Sketch under Moderate Clothing Change](https://mlsanity.com/paper/2002.02295/) (2020)
- [Part-Aligned Bilinear Representations for Person Re-identification](https://mlsanity.com/paper/1804.07094/) (2018)
- [On orthogonality and learning recurrent networks with long term dependencies](https://mlsanity.com/paper/1702.00071/) (2017)
- [Gait Recognition via Disentangled Representation Learning](https://mlsanity.com/paper/1904.04925/) (2019)
- [Appearance-Preserving 3D Convolution for Video-based Person Re-identification](https://mlsanity.com/paper/2007.08434/) (2020)
- [Efficient Orthogonal Parametrisation of Recurrent Neural Networks Using Householder Reflections](https://mlsanity.com/paper/1612.00188/) (2016)
- [When Person Re-identification Meets Changing Clothes](https://mlsanity.com/paper/2003.04070/) (2020)
- [Learning Debiased Classifier with Biased Committee](https://mlsanity.com/paper/2206.10843/) (2022)
- [Multi-scale Deep Learning Architectures for Person Re-identification](https://mlsanity.com/paper/1709.05165/) (2017)
- [Learning Disentangled Representation for Robust Person Re-identification](https://mlsanity.com/paper/1910.12003/) (2019)
- [OL'E: Orthogonal Low-rank Embedding, A Plug and Play Geometric Loss for Deep Learning](https://mlsanity.com/paper/1712.01727/) (2017)
- [COCAS: A Large-Scale Clothes Changing Person Dataset for Re-identification](https://mlsanity.com/paper/2005.07862/) (2020)
- [Feature Completion for Occluded Person Re-Identification](https://mlsanity.com/paper/2106.12733/) (2021)

## Built on by (most cited first, 1 of 1)

- [TSDW: A Tri-Stream Dynamic Weight Network for Cloth-Changing Person Re-Identification](https://mlsanity.com/paper/2503.00477/) (2025)

## Abstract (arXiv)

Cloth-Changing Person Re-Identification (CC-ReID) involves recognizing individuals in images regardless of clothing status. In this paper, we empirically and experimentally demonstrate that completely eliminating or fully retaining clothing features is detrimental to the task. Existing work, either relying on clothing labels, silhouettes, or other auxiliary data, fundamentally aim to balance the learning of clothing and identity features. However, we practically find that achieving this balance is challenging and nuanced. In this study, we introduce a novel module called Diverse Norm, which expands personal features into orthogonal spaces and employs channel attention to separate clothing and identity features. A sample re-weighting optimization strategy is also introduced to guarantee the opposite optimization direction. Diverse Norm presents a simple yet effective approach that does not require additional data. Furthermore, Diverse Norm can be seamlessly integrated ResNet50 and significantly outperforms the state-of-the-art methods.