# Learning Instance-Adaptive Low-Rank Orthogonal Subspaces for Clothes-Changing Person Re-Identification

arXiv: https://arxiv.org/abs/2606.11661 · HTML: https://mlsanity.com/paper/2606.11661/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 36 references that are in the map.
- First posted on arXiv 10 Jun 2026.

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://mlsanity.com/paper/2310.06824/) (2023)
- [Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection](https://mlsanity.com/paper/2004.07667/) (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)
- [Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification](https://mlsanity.com/paper/2211.11158/) (2022)
- [LEACE: Perfect linear concept erasure in closed form](https://mlsanity.com/paper/2306.03819/) (2023)
- [CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels](https://mlsanity.com/paper/2211.13977/) (2022)
- [Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)](https://mlsanity.com/paper/2402.10376/) (2024)
- [Linear Adversarial Concept Erasure](https://mlsanity.com/paper/2201.12091/) (2022)
- [Clothes-Changing Person Re-identification with RGB Modality Only](https://mlsanity.com/paper/2204.06890/) (2022)
- [Person Re-identification by Contour Sketch under Moderate Clothing Change](https://mlsanity.com/paper/2002.02295/) (2020)
- [Long-Term Cloth-Changing Person Re-identification](https://mlsanity.com/paper/2005.12633/) (2020)
- [Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularization](https://mlsanity.com/paper/2103.15537/) (2021)
- [LP++: A Surprisingly Strong Linear Probe for Few-Shot CLIP](https://mlsanity.com/paper/2404.02285/) (2024)
- [When Person Re-identification Meets Changing Clothes](https://mlsanity.com/paper/2003.04070/) (2020)
- [Large-Scale Spatio-Temporal Person Re-identification: Algorithms and Benchmark](https://mlsanity.com/paper/2105.15076/) (2021)
- [Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions](https://mlsanity.com/paper/2306.07520/) (2023)
- [Shape-Erased Feature Learning for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2304.04205/) (2023)
- [Learning Clothing and Pose Invariant 3D Shape Representation for Long-Term Person Re-Identification](https://mlsanity.com/paper/2308.10658/) (2023)
- [DIFFER: Disentangling Identity Features via Semantic Cues for Clothes-Changing Person Re-ID](https://mlsanity.com/paper/2503.22912/) (2025)
- [Colors See Colors Ignore: Clothes Changing ReID with Color Disentanglement](https://mlsanity.com/paper/2507.07230/) (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)

## Abstract (arXiv)

Clothes-changing person re-identification (CC-ReID) aims to recognize individuals despite drastic appearance changes caused by clothing variation. While existing methods rely on adversarial learning to disentangle clothing features, we propose Ortho-ReID, which explicitly models a low-rank clothing subspace from VLM text descriptions and extracts clothing-invariant representations via direct geometric constraints. A critical component is our transformer-based Basis Maker, which refines a shared, low-dimensional clothing prior into an instance-adaptive low-rank subspace through cross-attention with image patches, enabling robust clothing feature extraction even under varying visibility conditions. This instance-adaptive subspace is supervised via alignment with clothing text embeddings, while identity features are extracted via a learnable projection head and geometrically constrained to be strictly orthogonal to it. Extensive experiments demonstrate state-of-the-art performance on PRCC (+5.9% top-1), Celeb-reID-light (+3.5%), and LaST (+5.3%), with competitive results on LTCC.