Correspondence-Free Domain Alignment for Unsupervised Cross-Domain Image Retrieval

• URL: http://arxiv.org/abs/2302.06081v2
• Date: Thu, 23 Mar 2023 11:38:53 GMT
• Title: Correspondence-Free Domain Alignment for Unsupervised Cross-Domain Image Retrieval
• Authors: Xu Wang, Dezhong Peng, Ming Yan, Peng Hu
• Abstract summary: Cross-domain image retrieval aims at retrieving images across different domains to excavate cross-domain classificatory or correspondence relationships. It is challenging to align and bridge distinct domains without cross-domain correspondence. We present a novel Correspondence Domain-free Alignment (CoDA) method to eliminate the cross-domain gap. Our method could encode the discrimination into the domain-invariant embedding space for unsupervised cross-domain image retrieval.
• Score: 25.43019715242141
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Cross-domain image retrieval aims at retrieving images across different domains to excavate cross-domain classificatory or correspondence relationships. This paper studies a less-touched problem of cross-domain image retrieval, i.e., unsupervised cross-domain image retrieval, considering the following practical assumptions: (i) no correspondence relationship, and (ii) no category annotations. It is challenging to align and bridge distinct domains without cross-domain correspondence. To tackle the challenge, we present a novel Correspondence-free Domain Alignment (CoDA) method to effectively eliminate the cross-domain gap through In-domain Self-matching Supervision (ISS) and Cross-domain Classifier Alignment (CCA). To be specific, ISS is presented to encapsulate discriminative information into the latent common space by elaborating a novel self-matching supervision mechanism. To alleviate the cross-domain discrepancy, CCA is proposed to align distinct domain-specific classifiers. Thanks to the ISS and CCA, our method could encode the discrimination into the domain-invariant embedding space for unsupervised cross-domain image retrieval. To verify the effectiveness of the proposed method, extensive experiments are conducted on four benchmark datasets compared with six state-of-the-art methods.

Related papers

• DUDE: Diffusion-Based Unsupervised Cross-Domain Image Retrieval [25.89035776794712]
  Unsupervised cross-domain image retrieval (UCIR) aims to retrieve images of the same category across diverse domains without relying on annotations.<n>Existing UCIR methods, which align cross-domain features for the entire image, often struggle with the domain gap.<n>We propose DUDE, a novel UCIR method building upon feature disentanglement.
  arXiv  Detail & Related papers  (2025-09-04T13:15:16Z)
• Heterogeneous-Modal Unsupervised Domain Adaptation via Latent Space Bridging [12.171477896623148]
  We propose a novel setting called Heterogeneous-Modal Unsupervised Domain Adaptation (HMUDA)<n>HMUDA enables knowledge transfer between completely different modalities by leveraging a bridge domain containing unlabeled samples from both modalities.<n>We propose Latent Space Bridging (LSB), a specialized framework designed for the semantic segmentation task.
  arXiv  Detail & Related papers  (2025-06-19T02:31:51Z)
• From Limited Labels to Open Domains: An Efficient Learning Paradigm for UAV-view Geo-Localization [2.502228766495945]
  Traditional UAV-view Geo-Localization (UVGL) supervised paradigms are constrained by the strict reliance on paired data for positive sample selection. We propose a novel cross-domain invariance knowledge transfer network (CDIKTNet) Our method achieves state-of-the-art performance under fully supervised conditions.
  arXiv  Detail & Related papers  (2025-03-10T16:46:43Z)
• Joint Identifiability of Cross-Domain Recommendation via Hierarchical Subspace Disentanglement [19.29182848154183]
  Cross-Domain Recommendation (CDR) seeks to enable effective knowledge transfer across domains. While CDR describes user representations as a joint distribution over two domains, these methods fail to account for its joint identifiability. We propose a Hierarchical subspace disentanglement approach to explore the Joint IDentifiability of cross-domain joint distribution.
  arXiv  Detail & Related papers  (2024-04-06T03:11:31Z)
• Decompose to Adapt: Cross-domain Object Detection via Feature Disentanglement [79.2994130944482]
  We design a Domain Disentanglement Faster-RCNN (DDF) to eliminate the source-specific information in the features for detection task learning. Our DDF method facilitates the feature disentanglement at the global and local stages, with a Global Triplet Disentanglement (GTD) module and an Instance Similarity Disentanglement (ISD) module. By outperforming state-of-the-art methods on four benchmark UDA object detection tasks, our DDF method is demonstrated to be effective with wide applicability.
  arXiv  Detail & Related papers  (2022-01-06T05:43:01Z)
• Joint Distribution Alignment via Adversarial Learning for Domain Adaptive Object Detection [11.262560426527818]
  Unsupervised domain adaptive object detection aims to adapt a well-trained detector from its original source domain with rich labeled data to a new target domain with unlabeled data. Recently, mainstream approaches perform this task through adversarial learning, yet still suffer from two limitations. We propose a joint adaptive detection framework (JADF) to address the above challenges.
  arXiv  Detail & Related papers  (2021-09-19T00:27:08Z)
• Cross-domain Contrastive Learning for Unsupervised Domain Adaptation [108.63914324182984]
  Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a fully-labeled source domain to a different unlabeled target domain. We build upon contrastive self-supervised learning to align features so as to reduce the domain discrepancy between training and testing sets.
  arXiv  Detail & Related papers  (2021-06-10T06:32:30Z)
• AFAN: Augmented Feature Alignment Network for Cross-Domain Object Detection [90.18752912204778]
  Unsupervised domain adaptation for object detection is a challenging problem with many real-world applications. We propose a novel augmented feature alignment network (AFAN) which integrates intermediate domain image generation and domain-adversarial training. Our approach significantly outperforms the state-of-the-art methods on standard benchmarks for both similar and dissimilar domain adaptations.
  arXiv  Detail & Related papers  (2021-06-10T05:01:20Z)
• Bi-Dimensional Feature Alignment for Cross-Domain Object Detection [71.85594342357815]
  We propose a novel unsupervised cross-domain detection model. It exploits the annotated data in a source domain to train an object detector for a different target domain. The proposed model mitigates the cross-domain representation divergence for object detection.
  arXiv  Detail & Related papers  (2020-11-14T03:03:11Z)
• Discriminative Cross-Domain Feature Learning for Partial Domain Adaptation [70.45936509510528]
  Partial domain adaptation aims to adapt knowledge from a larger and more diverse source domain to a smaller target domain with less number of classes. Recent practice on domain adaptation manages to extract effective features by incorporating the pseudo labels for the target domain. It is essential to align target data with only a small set of source data.
  arXiv  Detail & Related papers  (2020-08-26T03:18:53Z)
• Unsupervised Cross-domain Image Classification by Distance Metric Guided Feature Alignment [11.74643883335152]
  Unsupervised domain adaptation is a promising avenue which transfers knowledge from a source domain to a target domain. We propose distance metric guided feature alignment (MetFA) to extract discriminative as well as domain-invariant features on both source and target domains. Our model integrates class distribution alignment to transfer semantic knowledge from a source domain to a target domain.
  arXiv  Detail & Related papers  (2020-08-19T13:36:57Z)
• Simultaneous Semantic Alignment Network for Heterogeneous Domain Adaptation [67.37606333193357]
  We propose aSimultaneous Semantic Alignment Network (SSAN) to simultaneously exploit correlations among categories and align the centroids for each category across domains. By leveraging target pseudo-labels, a robust triplet-centroid alignment mechanism is explicitly applied to align feature representations for each category. Experiments on various HDA tasks across text-to-image, image-to-image and text-to-text successfully validate the superiority of our SSAN against state-of-the-art HDA methods.
  arXiv  Detail & Related papers  (2020-08-04T16:20:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.