COME: Dual Structure-Semantic Learning with Collaborative MoE for Universal Lesion Detection Across Heterogeneous Ultrasound Datasets

• URL: http://arxiv.org/abs/2508.09886v1
• Date: Wed, 13 Aug 2025 15:43:20 GMT
• Title: COME: Dual Structure-Semantic Learning with Collaborative MoE for Universal Lesion Detection Across Heterogeneous Ultrasound Datasets
• Abstract summary: We propose a Universal Collaborative Mixture of Heterogeneous Source-Specific Experts (COME)<n>COME establishes dual structure-semantic shared experts that create a universal representation space and then collaborate with source-specific experts to extract discriminative features.<n>This design enables robust generalization by leveraging cross-datasets experience distributions and providing universal US priors for small-batch or unseen data scenarios.
• Score: 25.82307075214309
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Conventional single-dataset training often fails with new data distributions, especially in ultrasound (US) image analysis due to limited data, acoustic shadows, and speckle noise. Therefore, constructing a universal framework for multi-heterogeneous US datasets is imperative. However, a key challenge arises: how to effectively mitigate inter-dataset interference while preserving dataset-specific discriminative features for robust downstream task? Previous approaches utilize either a single source-specific decoder or a domain adaptation strategy, but these methods experienced a decline in performance when applied to other domains. Considering this, we propose a Universal Collaborative Mixture of Heterogeneous Source-Specific Experts (COME). Specifically, COME establishes dual structure-semantic shared experts that create a universal representation space and then collaborate with source-specific experts to extract discriminative features through providing complementary features. This design enables robust generalization by leveraging cross-datasets experience distributions and providing universal US priors for small-batch or unseen data scenarios. Extensive experiments under three evaluation modes (single-dataset, intra-organ, and inter-organ integration datasets) demonstrate COME's superiority, achieving significant mean AP improvements over state-of-the-art methods. Our project is available at: https://universalcome.github.io/UniversalCOME/.

Related papers

• Towards One-for-All Anomaly Detection for Tabular Data [87.63505963517512]
  Tabular anomaly detection (TAD) is critical in many real-world applications.<n>We propose OFA-TAD, a framework that only requires one-time training on multiple source datasets.<n>Experiments on 34 datasets from 14 domains demonstrate that OFA-TAD achieves superior anomaly detection performance.
  arXiv  Detail & Related papers  (2026-03-15T14:42:05Z)
• FedPrism: Adaptive Personalized Federated Learning under Non-IID Data [1.299941371793082]
  FedPrism is a framework that builds each client's model from three parts.<n>It uses a Prism Decomposition method that builds each client's model from three parts.<n>It also uses a Dual-Stream design that runs a general model alongside a local specialist.
  arXiv  Detail & Related papers  (2026-03-09T11:23:32Z)
• From Few-Shot to Zero-Shot: Towards Generalist Graph Anomaly Detection [89.52759572485276]
  ARC is a few-shot generalist GAD method that leverages in-context learning and requires only a few labeled normal samples at inference time.<n> ARC and ARC_zero effectively detect anomalies, exhibit strong generalization ability, and perform efficiently under few-shot and zero-shot settings.
  arXiv  Detail & Related papers  (2026-02-21T10:59:00Z)
• Mixture of Predefined Experts: Maximizing Data Usage on Vertical Federated Learning [4.1346825639910785]
  Split-MoPE is a novel framework that integrates Split Learning with a specialized Mixture of Predefined Experts architecture.<n>MoPE uses predefined experts to process specific data alignments, effectively maximizing data usage during both training and inference.<n>By leveraging pretrained encoders for target data domains, Split-MoPE achieves state-of-the-art performance in a single communication round.
  arXiv  Detail & Related papers  (2026-02-13T08:21:20Z)
• Towards Unified Multimodal Misinformation Detection in Social Media: A Benchmark Dataset and Baseline [56.790045049514326]
  Two major forms of deception dominate: human-crafted misinformation and AI-generated content.<n>We propose Unified Multimodal Fake Content Detection (UMFDet), a framework designed to handle both forms of deception.<n>UMFDet achieves robust and consistent performance across both misinformation types, outperforming specialized baselines.
  arXiv  Detail & Related papers  (2025-09-30T09:26:32Z)
• Uni$^2$Det: Unified and Universal Framework for Prompt-Guided Multi-dataset 3D Detection [64.08296187555095]
  Uni$2$Det is a framework for unified and universal multi-dataset training on 3D detection. We introduce multi-stage prompting modules for multi-dataset 3D detection. Results on zero-shot cross-dataset transfer validate the generalization capability of our proposed method.
  arXiv  Detail & Related papers  (2024-09-30T17:57:50Z)
• On-Device Collaborative Language Modeling via a Mixture of Generalists and Specialists [34.018740224268576]
  CoMiGS is a new approach to facilitate private learning on-device with scarce data.<n>It balances generalist experts across users while localizing a varying number of specialist experts.<n>We show CoMiGS effectively balances general and personalized knowledge for each token generation.
  arXiv  Detail & Related papers  (2024-09-20T22:34:37Z)
• Cross-Dataset Gaze Estimation by Evidential Inter-intra Fusion [38.93368421481945]
  We propose a novel Evidential Inter-intra Fusion EIF framework for training a cross-dataset model.<n>We build independent single-dataset branches for various datasets.<n>We further create a cross-dataset branch to integrate the generalizable features from single-dataset branches.
  arXiv  Detail & Related papers  (2024-09-07T08:53:17Z)
• Addressing Skewed Heterogeneity via Federated Prototype Rectification with Personalization [35.48757125452761]
  Federated learning is an efficient framework designed to facilitate collaborative model training across multiple distributed devices. A significant challenge of federated learning is data-level heterogeneity, i.e., skewed or long-tailed distribution of private data. We propose a novel Federated Prototype Rectification with Personalization which consists of two parts: Federated Personalization and Federated Prototype Rectification.
  arXiv  Detail & Related papers  (2024-08-15T06:26:46Z)
• ARC: A Generalist Graph Anomaly Detector with In-Context Learning [62.202323209244]
  ARC is a generalist GAD approach that enables a one-for-all'' GAD model to detect anomalies across various graph datasets on-the-fly.<n> equipped with in-context learning, ARC can directly extract dataset-specific patterns from the target dataset.<n>Extensive experiments on multiple benchmark datasets from various domains demonstrate the superior anomaly detection performance, efficiency, and generalizability of ARC.
  arXiv  Detail & Related papers  (2024-05-27T02:42:33Z)
• Source-Free Collaborative Domain Adaptation via Multi-Perspective Feature Enrichment for Functional MRI Analysis [55.03872260158717]
  Resting-state MRI functional (rs-fMRI) is increasingly employed in multi-site research to aid neurological disorder analysis. Many methods have been proposed to reduce fMRI heterogeneity between source and target domains. But acquiring source data is challenging due to concerns and/or data storage burdens in multi-site studies. We design a source-free collaborative domain adaptation framework for fMRI analysis, where only a pretrained source model and unlabeled target data are accessible.
  arXiv  Detail & Related papers  (2023-08-24T01:30:18Z)
• FedSIS: Federated Split Learning with Intermediate Representation Sampling for Privacy-preserving Generalized Face Presentation Attack Detection [4.1897081000881045]
  Lack of generalization to unseen domains/attacks is the Achilles heel of most face presentation attack detection (FacePAD) algorithms. In this work, a novel framework called Federated Split learning with Intermediate representation Sampling (FedSIS) is introduced for privacy-preserving domain generalization.
  arXiv  Detail & Related papers  (2023-08-20T11:49:12Z)
• DRFLM: Distributionally Robust Federated Learning with Inter-client Noise via Local Mixup [58.894901088797376]
  federated learning has emerged as a promising approach for training a global model using data from multiple organizations without leaking their raw data. We propose a general framework to solve the above two challenges simultaneously. We provide comprehensive theoretical analysis including robustness analysis, convergence analysis, and generalization ability.
  arXiv  Detail & Related papers  (2022-04-16T08:08:29Z)
• Shared Space Transfer Learning for analyzing multi-site fMRI data [83.41324371491774]
  Multi-voxel pattern analysis (MVPA) learns predictive models from task-based functional magnetic resonance imaging (fMRI) data. MVPA works best with a well-designed feature set and an adequate sample size. Most fMRI datasets are noisy, high-dimensional, expensive to collect, and with small sample sizes. This paper proposes the Shared Space Transfer Learning (SSTL) as a novel transfer learning approach.
  arXiv  Detail & Related papers  (2020-10-24T08:50:26Z)

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.