# Memory Regulation and Alignment toward Generalizer RGB-Infrared Person

arXiv: https://arxiv.org/abs/2109.08843 · HTML: https://mlsanity.com/paper/2109.08843/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 43 references that are in the map.
- First posted on arXiv 18 Sep 2021.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [Large-Scale Long-Tailed Recognition in an Open World](https://mlsanity.com/paper/1904.05160/) (2019)
- [Neural Turing Machines](https://mlsanity.com/paper/1410.5401/) (2014)
- [Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection](https://mlsanity.com/paper/1904.02639/) (2019)
- [Deep Learning for Person Re-identification: A Survey and Outlook](https://mlsanity.com/paper/2001.04193/) (2020)
- [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017)
- [Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)](https://mlsanity.com/paper/1711.09349/) (2017)
- [Circle Loss: A Unified Perspective of Pair Similarity Optimization](https://mlsanity.com/paper/2002.10857/) (2020)
- [Joint Discriminative and Generative Learning for Person Re-identification](https://mlsanity.com/paper/1904.07223/) (2019)
- [Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2007.09314/) (2020)
- [RGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignment](https://mlsanity.com/paper/1910.05839/) (2019)
- [Improving Person Re-identification by Attribute and Identity Learning](https://mlsanity.com/paper/1703.07220/) (2017)
- [Pose-driven Deep Convolutional Model for Person Re-identification](https://mlsanity.com/paper/1709.08325/) (2017)
- [Cross-modality Person re-identification with Shared-Specific Feature Transfer](https://mlsanity.com/paper/2002.12489/) (2020)
- [Cross-Modality Paired-Images Generation for RGB-Infrared Person Re-Identification](https://mlsanity.com/paper/2002.04114/) (2020)
- [Neural Feature Search for RGB-Infrared Person Re-Identification](https://mlsanity.com/paper/2104.02366/) (2021)
- [In Defense of the Triplet Loss Again: Learning Robust Person Re-Identification with Fast Approximated Triplet Loss and Label Distillation](https://mlsanity.com/paper/1912.07863/) (2019)
- [Learning and Memorizing Representative Prototypes for 3D Point Cloud Semantic and Instance Segmentation](https://mlsanity.com/paper/2001.01349/) (2020)
- [SBSGAN: Suppression of Inter-Domain Background Shift for Person Re-Identification](https://mlsanity.com/paper/1908.09086/) (2019)
- [EANet: Enhancing Alignment for Cross-Domain Person Re-identification](https://mlsanity.com/paper/1812.11369/) (2018)
- [Keep CALM and Improve Visual Feature Attribution](https://mlsanity.com/paper/2106.07861/) (2021)
- [Unsupervised Domain Adaptation for Person Re-Identification through Source-Guided Pseudo-Labeling](https://mlsanity.com/paper/2009.09445/) (2020)
- [Strong but Simple Baseline with Dual-Granularity Triplet Loss for Visible-Thermal Person Re-Identification](https://mlsanity.com/paper/2012.05010/) (2020)

## Built on by (most cited first, 2 of 2)

- [Memory augment is All You Need for image restoration](https://mlsanity.com/paper/2309.01377/) (2023)
- [Look Closer to Your Enemy: Learning to Attack via Teacher-Student Mimicking](https://mlsanity.com/paper/2207.13381/) (2022)

## Abstract (arXiv)

The domain shift, coming from unneglectable modality gap and non-overlapped identity classes between training and test sets, is a major issue of RGB-Infrared person re-identification. A key to tackle the inherent issue -- domain shift -- is to enforce the data distributions of the two domains to be similar. However, RGB-IR ReID always demands discriminative features, leading to over-rely feature sensitivity of seen classes, textite.g., via attention-based feature alignment or metric learning. Therefore, predicting the unseen query category from predefined training classes may not be accurate and leads to a sub-optimal adversarial gradient. In this paper, we uncover it in a more explainable way and propose a novel multi-granularity memory regulation and alignment module (MG-MRA) to solve this issue. By explicitly incorporating a latent variable attribute, from fine-grained to coarse semantic granularity, into intermediate features, our method could alleviate the over-confidence of the model about discriminative features of seen classes. Moreover, instead of matching discriminative features by traversing nearest neighbor, sparse attributes, textiti.e., global structural pattern, are recollected with respect to features and assigned to measure pair-wise image similarity in hashing. Extensive experiments on RegDB citeRegDB and SYSU-MM01 citeSYSU show the superiority of the proposed method that outperforms existing state-of-the-art methods. Our code is available in https://github.com/Chenfeng1271/MGMRA.