# TextAug: Test time Text Augmentation for Multimodal Person Re-identification

arXiv: https://arxiv.org/abs/2312.01605 · HTML: https://mlsanity.com/paper/2312.01605/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 48 references that are in the map.
- First posted on arXiv 4 Dec 2023.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Deep Visual-Semantic Alignments for Generating Image Descriptions](https://mlsanity.com/paper/1412.2306/) (2014)
- [LiT: Zero-Shot Transfer with Locked-image text Tuning](https://mlsanity.com/paper/2111.07991/) (2021)
- [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017)
- [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)
- [Zero-Shot Learning Through Cross-Modal Transfer](https://mlsanity.com/paper/1301.3666/) (2013)
- [Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations](https://mlsanity.com/paper/1805.06201/) (2018)
- [Learning Deep Representations of Fine-grained Visual Descriptions](https://mlsanity.com/paper/1605.05395/) (2016)
- [Person Search with Natural Language Description](https://mlsanity.com/paper/1702.05729/) (2017)
- [Augmenting Data with Mixup for Sentence Classification: An Empirical Study](https://mlsanity.com/paper/1905.08941/) (2019)
- [Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer](https://mlsanity.com/paper/2106.04095/) (2021)
- [Dual Attention Networks for Multimodal Reasoning and Matching](https://mlsanity.com/paper/1611.00471/) (2016)
- [Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification](https://mlsanity.com/paper/2107.12666/) (2021)
- [DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval](https://mlsanity.com/paper/2109.05534/) (2021)
- [See Finer, See More: Implicit Modality Alignment for Text-based Person Retrieval](https://mlsanity.com/paper/2208.08608/) (2022)
- [Identity-Aware Textual-Visual Matching with Latent Co-attention](https://mlsanity.com/paper/1708.01988/) (2017)
- [Batch DropBlock Network for Person Re-identification and Beyond](https://mlsanity.com/paper/1811.07130/) (2018)
- [Improving Deep Visual Representation for Person Re-identification by Global and Local Image-language Association](https://mlsanity.com/paper/1808.01571/) (2018)
- [Learning Paraphrastic Sentence Embeddings from Back-Translated Bitext](https://mlsanity.com/paper/1706.01847/) (2017)
- [Incomplete Descriptor Mining with Elastic Loss for Person Re-Identification](https://mlsanity.com/paper/2008.04010/) (2020)
- [Stripe-based and Attribute-aware Network: A Two-Branch Deep Model for Vehicle Re-identification](https://mlsanity.com/paper/1910.05549/) (2019)
- [One for More: Selecting Generalizable Samples for Generalizable ReID Model](https://mlsanity.com/paper/2012.05475/) (2020)
- [AMC: Attention guided Multi-modal Correlation Learning for Image Search](https://mlsanity.com/paper/1704.00763/) (2017)

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

- [Data Augmentation for Text-based Person Retrieval Using Large Language Models](https://mlsanity.com/paper/2405.11971/) (2024)

## Abstract (arXiv)

Multimodal Person Reidentification is gaining popularity in the research community due to its effectiveness compared to counter-part unimodal frameworks. However, the bottleneck for multimodal deep learning is the need for a large volume of multimodal training examples. Data augmentation techniques such as cropping, flipping, rotation, etc. are often employed in the image domain to improve the generalization of deep learning models. Augmenting in other modalities than images, such as text, is challenging and requires significant computational resources and external data sources. In this study, we investigate the effectiveness of two computer vision data augmentation techniques: cutout and cutmix, for text augmentation in multi-modal person re-identification. Our approach merges these two augmentation strategies into one strategy called CutMixOut which involves randomly removing words or sub-phrases from a sentence (Cutout) and blending parts of two or more sentences to create diverse examples (CutMix) with a certain probability assigned to each operation. This augmentation was implemented at inference time without any prior training. Our results demonstrate that the proposed technique is simple and effective in improving the performance on multiple multimodal person re-identification benchmarks.