# Unsupervised Cross-Domain Image Retrieval via Prototypical Optimal Transport

arXiv: https://arxiv.org/abs/2402.18411 · HTML: https://mlsanity.com/paper/2402.18411/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 41 references that are in the map.
- First posted on arXiv 28 Feb 2024.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [Prototypical Contrastive Learning of Unsupervised Representations](https://mlsanity.com/paper/2005.04966/) (2020)
- [Deep Transfer Learning with Joint Adaptation Networks](https://mlsanity.com/paper/1605.06636/) (2016)
- [Optimal Transport for Domain Adaptation](https://mlsanity.com/paper/1507.00504/) (2015)
- [Joint Distribution Optimal Transportation for Domain Adaptation](https://mlsanity.com/paper/1705.08848/) (2017)
- [Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation](https://mlsanity.com/paper/2103.16765/) (2021)
- [Optimal Transport for Multi-source Domain Adaptation under Target Shift](https://mlsanity.com/paper/1803.04899/) (2018)
- [Unified Optimal Transport Framework for Universal Domain Adaptation](https://mlsanity.com/paper/2210.17067/) (2022)
- [Cross-domain Image Retrieval with a Dual Attribute-aware Ranking Network](https://mlsanity.com/paper/1505.07922/) (2015)
- [StyleMeUp: Towards Style-Agnostic Sketch-Based Image Retrieval](https://mlsanity.com/paper/2103.15706/) (2021)
- [Unbalanced Optimal Transport, from Theory to Numerics](https://mlsanity.com/paper/2211.08775/) (2022)
- [Unbalanced Feature Transport for Exemplar-based Image Translation](https://mlsanity.com/paper/2106.10482/) (2021)
- [Accurate Point Cloud Registration with Robust Optimal Transport](https://mlsanity.com/paper/2111.00648/) (2021)
- [Bending Graphs: Hierarchical Shape Matching using Gated Optimal Transport](https://mlsanity.com/paper/2202.01537/) (2022)
- [Feature Representation Learning for Unsupervised Cross-domain Image Retrieval](https://mlsanity.com/paper/2207.09721/) (2022)
- [Cross-Domain Image Retrieval with Attention Modeling](https://mlsanity.com/paper/1709.01784/) (2017)
- [Correspondence-Free Domain Alignment for Unsupervised Cross-Domain Image Retrieval](https://mlsanity.com/paper/2302.06081/) (2023)
- [Adversarial Training Based Multi-Source Unsupervised Domain Adaptation for Sentiment Analysis](https://mlsanity.com/paper/2006.05602/) (2020)
- [MMFL-Net: Multi-scale and Multi-granularity Feature Learning for Cross-domain Fashion Retrieval](https://mlsanity.com/paper/2210.15128/) (2022)

## Built on by (most cited first, 7 of 7)

- [Global and Local Prompts Cooperation via Optimal Transport for Federated Learning](https://mlsanity.com/paper/2403.00041/) (2024)
- [Pre-training CLIP against Data Poisoning with Optimal Transport-based Matching and Alignment](https://mlsanity.com/paper/2509.18717/) (2025)
- [MADPOT: Medical Anomaly Detection with CLIP Adaptation and Partial Optimal Transport](https://mlsanity.com/paper/2507.06733/) (2025)
- [Differentiable Adaptive Kalman Filtering via Optimal Transport](https://mlsanity.com/paper/2508.07037/) (2025)
- [DUDE: Diffusion-Based Unsupervised Cross-Domain Image Retrieval](https://mlsanity.com/paper/2509.04193/) (2025)
- [Text-Phase Synergy Network with Dual Priors for Unsupervised Cross-Domain Image Retrieval](https://mlsanity.com/paper/2603.12711/) (2026)
- [SLAP: Selective Local Vision-Language Alignment for Fish Re-Identification via Partial Optimal Transport](https://mlsanity.com/paper/2608.08840/) (2026)

## Abstract (arXiv)

Unsupervised cross-domain image retrieval (UCIR) aims to retrieve images sharing the same category across diverse domains without relying on labeled data. Prior approaches have typically decomposed the UCIR problem into two distinct tasks: intra-domain representation learning and cross-domain feature alignment. However, these segregated strategies overlook the potential synergies between these tasks. This paper introduces ProtoOT, a novel Optimal Transport formulation explicitly tailored for UCIR, which integrates intra-domain feature representation learning and cross-domain alignment into a unified framework. ProtoOT leverages the strengths of the K-means clustering method to effectively manage distribution imbalances inherent in UCIR. By utilizing K-means for generating initial prototypes and approximating class marginal distributions, we modify the constraints in Optimal Transport accordingly, significantly enhancing its performance in UCIR scenarios. Furthermore, we incorporate contrastive learning into the ProtoOT framework to further improve representation learning. This encourages local semantic consistency among features with similar semantics, while also explicitly enforcing separation between features and unmatched prototypes, thereby enhancing global discriminativeness. ProtoOT surpasses existing state-of-the-art methods by a notable margin across benchmark datasets. Notably, on DomainNet, ProtoOT achieves an average P@200 enhancement of 18.17%, and on Office-Home, it demonstrates a P@15 improvement of 3.83%.