# A Theory-Inspired Framework for Few-Shot Cross-Modal Sketch Person Re-Identification

arXiv: https://arxiv.org/abs/2511.18677 · HTML: https://mlsanity.com/paper/2511.18677/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 54 references that are in the map.
- First posted on arXiv 24 Nov 2025.

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

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [Universal adversarial perturbations](https://mlsanity.com/paper/1610.08401/) (2016)
- [Generalizing to Unseen Domains via Adversarial Data Augmentation](https://mlsanity.com/paper/1805.12018/) (2018)
- [Re-ranking Person Re-identification with k-reciprocal Encoding](https://mlsanity.com/paper/1701.08398/) (2017)
- [Dissecting Person Re-identification from the Viewpoint of Viewpoint](https://mlsanity.com/paper/1812.02162/) (2018)
- [Diverse Embedding Expansion Network and Low-Light Cross-Modality Benchmark for Visible-Infrared Person Re-identification](https://mlsanity.com/paper/2303.14481/) (2023)
- [Learning Meta Face Recognition in Unseen Domains](https://mlsanity.com/paper/2003.07733/) (2020)
- [Person Re-identification Method Based on Color Attack and Joint Defence](https://mlsanity.com/paper/2111.09571/) (2021)
- [Cross-Modality Perturbation Synergy Attack for Person Re-identification](https://mlsanity.com/paper/2401.10090/) (2024)
- [Eliminate Deviation with Deviation for Data Augmentation and a General Multi-modal Data Learning Method](https://mlsanity.com/paper/2101.08533/) (2021)
- [Magic Tokens: Select Diverse Tokens for Multi-modal Object Re-Identification](https://mlsanity.com/paper/2403.10254/) (2024)
- [Towards Universal Modal Tracking with Online Dense Temporal Token Learning](https://mlsanity.com/paper/2507.20177/) (2025)
- [Beyond Augmentation: Empowering Model Robustness under Extreme Capture Environments](https://mlsanity.com/paper/2407.13640/) (2024)
- [Learn from Downstream and Be Yourself in Multimodal Large Language Model Fine-Tuning](https://mlsanity.com/paper/2411.10928/) (2024)
- [All in One Framework for Multimodal Re-identification in the Wild](https://mlsanity.com/paper/2405.04741/) (2024)
- [CIFAR-10-Warehouse: Broad and More Realistic Testbeds in Model Generalization Analysis](https://mlsanity.com/paper/2310.04414/) (2023)
- [Robust Self-Paced Hashing for Cross-Modal Retrieval with Noisy Labels](https://mlsanity.com/paper/2501.01699/) (2025)
- [Shape-centered Representation Learning for Visible-Infrared Person Re-identification](https://mlsanity.com/paper/2310.17952/) (2023)
- [LLaVA-ReID: Selective Multi-image Questioner for Interactive Person Re-Identification](https://mlsanity.com/paper/2504.10174/) (2025)
- [Video-Level Language-Driven Video-Based Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2506.02439/) (2025)
- [Hierarchical Bi-Directional Feature Perception Network for Person Re-Identification](https://mlsanity.com/paper/2008.03509/) (2020)
- [Alice Benchmarks: Connecting Real World Re-Identification with the Synthetic](https://mlsanity.com/paper/2310.04416/) (2023)
- [Robust Duality Learning for Unsupervised Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2505.02549/) (2025)
- [Beyond Domain Gap: Exploiting Subjectivity in Sketch-Based Person Retrieval](https://mlsanity.com/paper/2309.08372/) (2023)

## Built on by (most cited first, 5 of 5)

- [Statistical Characteristic-Guided Denoising for Rapid High-Resolution Transmission Electron Microscopy Imaging](https://mlsanity.com/paper/2603.18834/) (2026)
- [GS-STVSR: Ultra-Efficient Continuous Spatio-Temporal Video Super-Resolution via 2D Gaussian Splatting](https://mlsanity.com/paper/2604.18047/) (2026)
- [ReconMIL: Synergizing Latent Space Reconstruction with Bi-Stream Mamba for Whole Slide Image Analysis](https://mlsanity.com/paper/2603.19925/) (2026)
- [Open-Linguistic Concept Unified Learning for Cross-Site Interpretable Dermatology Image Diagnosis](https://mlsanity.com/paper/2608.03225/) (2026)
- [Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence](https://mlsanity.com/paper/2608.07987/) (2026)

## Abstract (arXiv)

Sketch based person re-identification aims to match hand-drawn sketches with RGB surveillance images, but remains challenging due to significant modality gaps and limited annotated data. To address this, we introduce KTCAA, a theoretically grounded framework for few-shot cross-modal generalization. Motivated by generalization theory, we identify two key factors influencing target domain risk: (1) domain discrepancy, which quantifies the alignment difficulty between source and target distributions; and (2) perturbation invariance, which evaluates the model's robustness to modality shifts. Based on these insights, we propose two components: (1) Alignment Augmentation (AA), which applies localized sketch-style transformations to simulate target distributions and facilitate progressive alignment; and (2) Knowledge Transfer Catalyst (KTC), which enhances invariance by introducing worst-case perturbations and enforcing consistency. These modules are jointly optimized under a meta-learning paradigm that transfers alignment knowledge from data-rich RGB domains to sketch-based scenarios. Experiments on multiple benchmarks demonstrate that KTCAA achieves state-of-the-art performance, particularly in data-scarce conditions.