# Not All Starting Points Are Equal: Pre-trained Priors and Their Outsized Impact on Person Identification

arXiv: https://arxiv.org/abs/2507.17640 · HTML: https://mlsanity.com/paper/2507.17640/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 49 references that are in the map.
- First posted on arXiv 23 Jul 2025.

## Builds on (most cited first, 30 of 32)

- [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)
- [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)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [Language Modeling with Gated Convolutional Networks](https://mlsanity.com/paper/1612.08083/) (2016)
- [EVA: Exploring the Limits of Masked Visual Representation Learning at Scale](https://mlsanity.com/paper/2211.07636/) (2022)
- [Deep Learning for Person Re-identification: A Survey and Outlook](https://mlsanity.com/paper/2001.04193/) (2020)
- [TransReID: Transformer-based Object Re-Identification](https://mlsanity.com/paper/2102.04378/) (2021)
- [EVA-02: A Visual Representation for Neon Genesis](https://mlsanity.com/paper/2303.11331/) (2023)
- [CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels](https://mlsanity.com/paper/2211.13977/) (2022)
- [A General Framework for Updating Belief Distributions](https://mlsanity.com/paper/1306.6430/) (2013)
- [Clothes-Changing Person Re-identification with RGB Modality Only](https://mlsanity.com/paper/2204.06890/) (2022)
- [Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks](https://mlsanity.com/paper/2303.17602/) (2023)
- [Long-Term Cloth-Changing Person Re-identification](https://mlsanity.com/paper/2005.12633/) (2020)
- [Expanding Accurate Person Recognition to New Altitudes and Ranges: The BRIAR Dataset](https://mlsanity.com/paper/2211.01917/) (2022)
- [Large-Scale Spatio-Temporal Person Re-identification: Algorithms and Benchmark](https://mlsanity.com/paper/2105.15076/) (2021)
- [HAT: Hierarchical Aggregation Transformers for Person Re-identification](https://mlsanity.com/paper/2107.05946/) (2021)
- [Self-Supervised Pre-Training for Transformer-Based Person Re-Identification](https://mlsanity.com/paper/2111.12084/) (2021)
- [COCAS: A Large-Scale Clothes Changing Person Dataset for Re-identification](https://mlsanity.com/paper/2005.07862/) (2020)
- [Person Re-Identification with a Locally Aware Transformer](https://mlsanity.com/paper/2106.03720/) (2021)
- [DeepChange: A Large Long-Term Person Re-Identification Benchmark with Clothes Change](https://mlsanity.com/paper/2105.14685/) (2021)
- [DIFFER: Disentangling Identity Features via Semantic Cues for Clothes-Changing Person Re-ID](https://mlsanity.com/paper/2503.22912/) (2025)
- [Recognizing People by Body Shape Using Deep Networks of Images and Words](https://mlsanity.com/paper/2305.19160/) (2023)
- [CILP-FGDI: Exploiting Vision-Language Model for Generalizable Person Re-Identification](https://mlsanity.com/paper/2501.16065/) (2025)
- [Masked Attribute Description Embedding for Cloth-Changing Person Re-identification](https://mlsanity.com/paper/2401.05646/) (2024)
- [CLIP-Driven Cloth-Agnostic Feature Learning for Cloth-Changing Person Re-Identification](https://mlsanity.com/paper/2406.09198/) (2024)
- [Dissecting Human Body Representations in Deep Networks Trained for Person Identification](https://mlsanity.com/paper/2502.15934/) (2025)

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

- [Face, Whole-Person, and Object Classification in a Unified Space Via The Interleaved Multi-Domain Identity Curriculum](https://mlsanity.com/paper/2511.19846/) (2025)

## Abstract (arXiv)

Recent years have seen an explosion of diverse general purpose pre-training methodologies for computer vision. However, the impact that these pre-training methodologies have on person identification tasks (re-id) remains under-explored. We show that under equated domain adaptation pipelines, there is dramatic variance in person identification outcomes using different starting models (architectures and pre-trained weights). We show that a range of intuitive explanations for differing downstream performance on a range of re-id tests are insufficient and propose that pre-trained weights serve as a strong prior to the weights learned during domain adaptation. This framework allows for domain adapted solutions to be viewed as a maximum probability point estimate of the Gibbs posterior with the pre-trained weights acting as a prior. Under this framework, we show that large, pre-trained foundation models with simple domain adaptation achieve SOTA solutions on a range of re-id datasets (Market, PRCC, DeepChange, BTS) with solutions that are very close in the parameter space to the starting parameters. Moreover, we perform ablations on these solutions and show that they can be reached with small transfer sets and with varying transfer datasets but are sensitive to choice of optimizer, weight-decay, and loss function. Ultimately, we propose that the simple approach of direct fine-tuning using large vision foundation models (CLIP, Dino, EVA, AIM, etc.) needs to serve as an important baseline for future work in re-id.