mlsanityData to 14 Oct 2026

DUDE: Diffusion-Based Unsupervised Cross-Domain Image Retrieval

arXiv 2509.04193 ↗First posted 4 Sep 2025cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Unsupervised cross-domain image retrieval (UCIR) aims to retrieve images of the same category across diverse domains without relying on annotations. Existing UCIR methods, which align cross-domain features for the entire image, often struggle with the domain gap, as the object features critical for retrieval are frequently entangled with domain-specific styles. To address this challenge, we propose DUDE, a novel UCIR method building upon feature disentanglement. In brief, DUDE leverages a text-to-image generative model to disentangle object features from domain-specific styles, thus facilitating semantical image retrieval. To further achieve reliable alignment of the disentangled object features, DUDE aligns mutual neighbors from within domains to across domains in a progressive manner. Extensive experiments demonstrate that DUDE achieves state-of-the-art performance across three benchmark datasets over 13 domains. The code will be released.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 35 of its 55 references that are in the map. First posted on arXiv 4 Sep 2025.

Builds on

35 of 55 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  6. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  7. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,845
  8. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,331
  9. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,188
  10. 2022Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generationcited by 961
  11. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 762
  12. 2024Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Thinkcited by 703
23 more
  1. 2020Prototypical Contrastive Learning of Unsupervised Representationscited by 640
  2. 2023ControlVideo: Training-free Controllable Text-to-Video Generationcited by 327
  3. 2023A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondencecited by 301
  4. 2021A Fourier-based Framework for Domain Generalizationcited by 290
  5. 2021SegDiff: Image Segmentation with Diffusion Probabilistic Modelscited by 280
  6. 2023Ambiguous Medical Image Segmentation using Diffusion Modelscited by 92
  7. 2016Disentangling factors of variation in deep representations using adversarial trainingcited by 87
  8. 2021Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptationcited by 83
  9. 2023CLIP for All Things Zero-Shot Sketch-Based Image Retrieval, Fine-Grained or Notcited by 79
  10. 2019Self-supervised Domain Adaptation for Computer Vision Taskscited by 58
  11. 2015Cross-domain Image Retrieval with a Dual Attribute-aware Ranking Networkcited by 53
  12. 2023StyleAdapter: A Unified Stylized Image Generation Modelcited by 39
  13. 2023Picture that Sketch: Photorealistic Image Generation from Abstract Sketchescited by 34
  14. 2022Feature Representation Learning for Unsupervised Cross-domain Image Retrievalcited by 17
  15. 2017Cross-Domain Image Retrieval with Attention Modelingcited by 14
  16. 2023Learning Dynamic Style Kernels for Artistic Style Transfercited by 12
  17. 2023Correspondence-Free Domain Alignment for Unsupervised Cross-Domain Image Retrievalcited by 11
  18. 2022Reducing Domain Gap in Frequency and Spatial domain for Cross-modality Domain Adaptation on Medical Image Segmentationcited by 10
  19. 2022StyleID: Identity Disentanglement for Anonymizing Facescited by 10
  20. 2022FAST: Improving Controllability for Text Generation with Feedback Aware Self-Trainingcited by 7
  21. 2023Data-Free Sketch-Based Image Retrievalcited by 7
  22. 2024Unsupervised Cross-Domain Image Retrieval via Prototypical Optimal Transportcited by 7
  23. 2022MMFL-Net: Multi-scale and Multi-granularity Feature Learning for Cross-domain Fashion Retrievalcited by 2

Built on by

Not cited yet.