Multiple Noises in Diffusion Model for Semi-Supervised Multi-Domain Translation

• URL: http://arxiv.org/abs/2309.14394v2
• Date: Sat, 06 Sep 2025 01:14:24 GMT
• Title: Multiple Noises in Diffusion Model for Semi-Supervised Multi-Domain Translation
• Authors: Tsiry Mayet, Simon Bernard, Romain Herault, Clement Chatelain,
• Abstract summary: We introduce Multi-Domain Diffusion (MDD) to solve the challenge of multi-domain translation.<n>MDD reconstructs missing views for new data objects, and enables learning in semi-supervised contexts.<n>We evaluate our approach through domain translation experiments on BL3NDT, a multi-domain synthetic dataset.
• Score: 1.9510388605988505
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: In this work, we address the challenge of multi-domain translation, where the objective is to learn mappings between arbitrary configurations of domains within a defined set (such as $(D_1, D_2)\rightarrow{}D_3$, $D_2\rightarrow{}(D_1, D_3)$, $D_3\rightarrow{}D_1$, etc. for three domains) without the need for separate models for each specific translation configuration, enabling more efficient and flexible domain translation. We introduce Multi-Domain Diffusion (MDD), a method with dual purposes: i) reconstructing any missing views for new data objects, and ii) enabling learning in semi-supervised contexts with arbitrary supervision configurations. MDD achieves these objectives by exploiting the noise formulation of diffusion models, specifically modeling one noise level per domain. Similar to existing domain translation approaches, MDD learns the translation between any combination of domains. However, unlike prior work, our formulation inherently handles semi-supervised learning without modification by representing missing views as noise in the diffusion process. We evaluate our approach through domain translation experiments on BL3NDT, a multi-domain synthetic dataset designed for challenging semantic domain inversion, the BraTS2020 dataset, and the CelebAMask-HQ dataset.

Related papers

• Universal Multi-Domain Translation via Diffusion Routers [23.85537575452933]
  Multi-domain translation (MDT) aims to learn translations between multiple domains, yet existing approaches either require fully aligneds or can only handle domain pairs seen in training.<n>We introduce universal MDT (UMDT), a generalization of MDT that seeks to translate between any pair of $K$ domains using only $K-1$ paired with a central domain.<n>We propose Diffusion Router (DR), a unified diffusion-based framework that models all central$leftarrow$non-central translations with a single noise predictor.
  arXiv  Detail & Related papers  (2025-09-26T07:32:43Z)
• LADB: Latent Aligned Diffusion Bridges for Semi-Supervised Domain Translation [54.690154688667086]
  Diffusion models excel at generating high-quality outputs but face challenges in data-scarce domains.<n>We propose Latent Aligned Diffusion Bridges (LADB), a semi-supervised framework for sample-to-sample translation.
  arXiv  Detail & Related papers  (2025-09-10T14:23:07Z)
• Let Synthetic Data Shine: Domain Reassembly and Soft-Fusion for Single Domain Generalization [68.41367635546183]
  Single Domain Generalization aims to train models with consistent performance across diverse scenarios using data from a single source.<n>We propose Discriminative Domain Reassembly and Soft-Fusion (DRSF), a training framework leveraging synthetic data to improve model generalization.
  arXiv  Detail & Related papers  (2025-03-17T18:08:03Z)
• Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentation [65.78246406460305]
  compositional semantic mixing represents the first unsupervised domain adaptation technique for point cloud segmentation. We present a two-branch symmetric network architecture capable of concurrently processing point clouds from a source domain (e.g. synthetic) and point clouds from a target domain (e.g. real-world)
  arXiv  Detail & Related papers  (2023-08-28T14:43:36Z)
• Domain-Scalable Unpaired Image Translation via Latent Space Anchoring [88.7642967393508]
  Unpaired image-to-image translation (UNIT) aims to map images between two visual domains without paired training data. We propose a new domain-scalable UNIT method, termed as latent space anchoring. Our method anchors images of different domains to the same latent space of frozen GANs by learning lightweight encoder and regressor models. In the inference phase, the learned encoders and decoders of different domains can be arbitrarily combined to translate images between any two domains without fine-tuning.
  arXiv  Detail & Related papers  (2023-06-26T17:50:02Z)
• Modular Domain Adaptation for Conformer-Based Streaming ASR [28.398302172150636]
  We propose a framework that enables a single model to process multidomain data while keeping all parameters domain-specific. On a streaming Conformer transducer trained only on video caption data, experimental results show that an MDA-based model can reach similar performance as the multidomain model on other domains.
  arXiv  Detail & Related papers  (2023-05-22T18:49:35Z)
• DORIC : Domain Robust Fine-Tuning for Open Intent Clustering through Dependency Parsing [14.709084509818474]
  DSTC11-Track2 aims to provide a benchmark for zero-shot, cross-domain, intent-set induction. We leveraged a multi-domain dialogue dataset to fine-tune the language model and proposed extracting Verb-Object pairs. Our approach achieved 3rd place in the precision score and showed superior accuracy and normalized mutual information (NMI) score than the baseline model.
  arXiv  Detail & Related papers  (2023-03-17T08:12:36Z)
• Domain Translation via Latent Space Mapping [1.1470070927586016]
  We introduce a new unified framework called Latent Space Mapping (model) Unlike existing approaches, we propose to further regularize each latent space using available domains by learning each dependency between pairs of domains.
  arXiv  Detail & Related papers  (2022-12-06T23:09:40Z)
• Domain-General Crowd Counting in Unseen Scenarios [25.171343652312974]
  Domain shift across crowd data severely hinders crowd counting models to generalize to unseen scenarios. We introduce a dynamic sub-domain division scheme which divides the source domain into multiple sub-domains. In order to disentangle domain-invariant information from domain-specific information in image features, we design the domain-invariant and -specific crowd memory modules.
  arXiv  Detail & Related papers  (2022-12-05T19:52:28Z)
• M2D2: A Massively Multi-domain Language Modeling Dataset [76.13062203588089]
  We present M2D2, a fine-grained, massively multi-domain corpus for studying domain adaptation (LMs) Using categories derived from Wikipedia and ArXiv, we organize the domains in each data source into 22 groups. We show the benefits of adapting the LM along a domain hierarchy; adapting to smaller amounts of fine-grained domain-specific data can lead to larger in-domain performance gains.
  arXiv  Detail & Related papers  (2022-10-13T21:34:52Z)
• Multi-Modal Cross-Domain Alignment Network for Video Moment Retrieval [55.122020263319634]
  Video moment retrieval (VMR) aims to localize the target moment from an untrimmed video according to a given language query. In this paper, we focus on a novel task: cross-domain VMR, where fully-annotated datasets are available in one domain but the domain of interest only contains unannotated datasets. We propose a novel Multi-Modal Cross-Domain Alignment network to transfer the annotation knowledge from the source domain to the target domain.
  arXiv  Detail & Related papers  (2022-09-23T12:58:20Z)
• Dynamic Instance Domain Adaptation [109.53575039217094]
  Most studies on unsupervised domain adaptation assume that each domain's training samples come with domain labels. We develop a dynamic neural network with adaptive convolutional kernels to generate instance-adaptive residuals to adapt domain-agnostic deep features to each individual instance. Our model, dubbed DIDA-Net, achieves state-of-the-art performance on several commonly used single-source and multi-source UDA datasets.
  arXiv  Detail & Related papers  (2022-03-09T20:05:54Z)
• Efficient Hierarchical Domain Adaptation for Pretrained Language Models [77.02962815423658]
  Generative language models are trained on diverse, general domain corpora. We introduce a method to scale domain adaptation to many diverse domains using a computationally efficient adapter approach.
  arXiv  Detail & Related papers  (2021-12-16T11:09:29Z)
• Adaptive Hierarchical Dual Consistency for Semi-Supervised Left Atrium Segmentation on Cross-Domain Data [8.645556125521246]
  Generalising semi-supervised learning to cross-domain data is of high importance to improve model robustness. The AHDC consists of a Bidirectional Adversarial Inference module (BAI) and a Hierarchical Dual Consistency learning module (HDC) We demonstrate the performance of our proposed AHDC on four 3D late gadolinium enhancement cardiac MR (LGE-CMR) datasets from different centres and a 3D CT dataset.
  arXiv  Detail & Related papers  (2021-09-17T02:15:10Z)
• IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID [58.46907388691056]
  We argue that the bridging between the source and target domains can be utilized to tackle the UDA re-ID task. We propose an Intermediate Domain Module (IDM) to generate intermediate domains' representations on-the-fly. Our proposed method outperforms the state-of-the-arts by a large margin in all the common UDA re-ID tasks.
  arXiv  Detail & Related papers  (2021-08-05T07:19:46Z)
• Dynamic Transfer for Multi-Source Domain Adaptation [82.54405157719641]
  We present dynamic transfer to address domain conflicts, where the model parameters are adapted to samples. It breaks down source domain barriers and turns multi-source domains into a single-source domain. Experimental results show that, without using domain labels, our dynamic transfer outperforms the state-of-the-art method by more than 3%.
  arXiv  Detail & Related papers  (2021-03-19T01:22:12Z)
• Iterative Domain-Repaired Back-Translation [50.32925322697343]
  In this paper, we focus on the domain-specific translation with low resources, where in-domain parallel corpora are scarce or nonexistent. We propose a novel iterative domain-repaired back-translation framework, which introduces the Domain-Repair model to refine translations in synthetic bilingual data. Experiments on adapting NMT models between specific domains and from the general domain to specific domains demonstrate the effectiveness of our proposed approach.
  arXiv  Detail & Related papers  (2020-10-06T04:38:09Z)
• Unified Multi-Domain Learning and Data Imputation using Adversarial Autoencoder [5.933303832684138]
  We present a novel framework that can combine multi-domain learning (MDL), data imputation (DI) and multi-task learning (MTL) The core of our method is an adversarial autoencoder that can: (1) learn to produce domain-invariant embeddings to reduce the difference between domains; (2) learn the data distribution for each domain and correctly perform data imputation on missing data.
  arXiv  Detail & Related papers  (2020-03-15T19:55:07Z)
• MADAN: Multi-source Adversarial Domain Aggregation Network for Domain Adaptation [58.38749495295393]
  Domain adaptation aims to learn a transferable model to bridge the domain shift between one labeled source domain and another sparsely labeled or unlabeled target domain. Recent multi-source domain adaptation (MDA) methods do not consider the pixel-level alignment between sources and target. We propose a novel MDA framework to address these challenges.
  arXiv  Detail & Related papers  (2020-02-19T21:22:00Z)

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.