# PartFormer: Awakening Latent Diverse Representation from Vision Transformer for Object Re-Identification

arXiv: https://arxiv.org/abs/2408.16684 · HTML: https://mlsanity.com/paper/2408.16684/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 34 references that are in the map.
- First posted on arXiv 29 Aug 2024.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [Deep Learning for Person Re-identification: A Survey and Outlook](https://mlsanity.com/paper/2001.04193/) (2020)
- [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)
- [Learning Discriminative Features with Multiple Granularities for Person Re-Identification](https://mlsanity.com/paper/1804.01438/) (2018)
- [Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro](https://mlsanity.com/paper/1701.07717/) (2017)
- [AdaViT: Adaptive Vision Transformers for Efficient Image Recognition](https://mlsanity.com/paper/2111.15668/) (2021)
- [Joint Discriminative and Generative Learning for Person Re-identification](https://mlsanity.com/paper/1904.07223/) (2019)
- [ABD-Net: Attentive but Diverse Person Re-Identification](https://mlsanity.com/paper/1908.01114/) (2019)
- [Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer](https://mlsanity.com/paper/2106.04095/) (2021)
- [Identity-Guided Human Semantic Parsing for Person Re-Identification](https://mlsanity.com/paper/2007.13467/) (2020)
- [Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification](https://mlsanity.com/paper/2205.02151/) (2022)
- [Pose-guided Feature Disentangling for Occluded Person Re-identification Based on Transformer](https://mlsanity.com/paper/2112.02466/) (2021)
- [Parsing-based View-aware Embedding Network for Vehicle Re-Identification](https://mlsanity.com/paper/2004.05021/) (2020)
- [Exploring Spatial Significance via Hybrid Pyramidal Graph Network for Vehicle Re-identification](https://mlsanity.com/paper/2005.14684/) (2020)
- [Uncertainty-Aware Multi-Shot Knowledge Distillation for Image-Based Object Re-Identification](https://mlsanity.com/paper/2001.05197/) (2020)
- [Part-Guided Attention Learning for Vehicle Instance Retrieval](https://mlsanity.com/paper/1909.06023/) (2019)

## Built on by (most cited first, 13 of 13)

- [RLE: A Unified Perspective of Data Augmentation for Cross-Spectral Re-identification](https://mlsanity.com/paper/2411.01225/) (2024)
- [3DOT: Texture Transfer for 3DGS Objects from a Single Reference Image](https://mlsanity.com/paper/2503.18853/) (2025)
- [MDReID: Modality-Decoupled Learning for Any-to-Any Multi-Modal Object Re-Identification](https://mlsanity.com/paper/2510.23301/) (2025)
- [GSAlign: Geometric and Semantic Alignment Network for Aerial-Ground Person Re-Identification](https://mlsanity.com/paper/2510.22268/) (2025)
- [Knowing Where to Focus: Attention-Guided Alignment for Text-based Person Search](https://mlsanity.com/paper/2412.15106/) (2024)
- [CityGuard: Graph-Aware Private Descriptors for Bias-Resilient Identity Search Across Urban Cameras](https://mlsanity.com/paper/2602.18047/) (2026)
- [Gen2Physics: Grounding Generated 3D Meshes in Physics via Multi-View Material Decomposition](https://mlsanity.com/paper/2608.23869/) (2026)
- [ReIDMamba: Learning Discriminative Features with Visual State Space Model for Person Re-Identification](https://mlsanity.com/paper/2511.07948/) (2025)
- [Rectifying Geometry-Induced Similarity Distortions for Real-World Aerial-Ground Person Re-Identification](https://mlsanity.com/paper/2601.21405/) (2026)
- [DPM++: Dynamic Masked Metric Learning for Occluded Person Re-identification](https://mlsanity.com/paper/2605.06637/) (2026)
- [FUSE: Frequency-domain Unification and Spectral Energy Alignment for Multi-modal Object Re-Identification](https://mlsanity.com/paper/2606.20044/) (2026)
- [Blurring Modal Boundaries: A Unified Survey from Single- to Multi-Modal Person Re-ldentification](https://mlsanity.com/paper/2607.14821/) (2026)
- [Reliability-Aware 3D Geometric Injection for Universal Person Re-identification](https://mlsanity.com/paper/2607.18863/) (2026)

## Abstract (arXiv)

Extracting robust feature representation is critical for object re-identification to accurately identify objects across non-overlapping cameras. Although having a strong representation ability, the Vision Transformer (ViT) tends to overfit on most distinct regions of training data, limiting its generalizability and attention to holistic object features. Meanwhile, due to the structural difference between CNN and ViT, fine-grained strategies that effectively address this issue in CNN do not continue to be successful in ViT. To address this issue, by observing the latent diverse representation hidden behind the multi-head attention, we present PartFormer, an innovative adaptation of ViT designed to overcome the granularity limitations in object Re-ID tasks. The PartFormer integrates a Head Disentangling Block (HDB) that awakens the diverse representation of multi-head self-attention without the typical loss of feature richness induced by concatenation and FFN layers post-attention. To avoid the homogenization of attention heads and promote robust part-based feature learning, two head diversity constraints are imposed: attention diversity constraint and correlation diversity constraint. These constraints enable the model to exploit diverse and discriminative feature representations from different attention heads. Comprehensive experiments on various object Re-ID benchmarks demonstrate the superiority of the PartFormer. Specifically, our framework significantly outperforms state-of-the-art by 2.4% mAP scores on the most challenging MSMT17 dataset.