SNR-Adaptive Unified Diffusion for Multi-Task Medical Image Segmentation

• URL: http://arxiv.org/abs/2607.03103v1
• Date: Fri, 03 Jul 2026 08:38:39 GMT
• Title: SNR-Adaptive Unified Diffusion for Multi-Task Medical Image Segmentation
• Abstract summary: We present UniT-Diff, a unified diffusion segmentation framework that resolves conflicts through three targeted mechanisms.<n>An 11-channel task-specific output space physically partitions label categories, eliminating cross-task gradient sign reversal by construction.<n>UniT-Diff surpasses independently trained task-specific baselines on all three benchmarks simultaneously.
• Score: 25.247512963111408
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Clinical cardiac imaging pipelines currently deploy separate models for each dataset and modality, incurring redundant training costs and precluding knowledge sharing across anatomically related tasks. Consolidating semi-supervised learning, unsupervised domain adaptation, and domain generalisation into one model is therefore a practical necessity, yet naive joint training exposes a fundamental barrier: conflicting label semantics between datasets collapse LA Dice from 90.31\% to 83.38\%, while gradient imbalance across tasks of unequal complexity suppresses the weaker tasks throughout training. We present UniT-Diff, a unified diffusion segmentation framework that resolves these conflicts through three targeted mechanisms. An 11-channel task-specific output space physically partitions label categories, eliminating cross-task gradient sign reversal by construction. SNR-Adaptive Task Conditioning (SATC) scales the task token by the log signal-to-noise ratio of the current diffusion timestep, suppressing domain-specific bias during coarse denoising and restoring full task guidance as the signal clears. Task-Type-Aware Conditional Dropout (TTACD) permanently removes the task token for domain-generalisation inputs, routing them through a shared neutral pathway that draws on cross-dataset cardiac anatomy rather than source-vendor statistics. Under a single parameter set, UniT-Diff surpasses independently trained task-specific baselines on all three benchmarks simultaneously: +0.87\% on LA, +1.77\% on MMWHS, and +0.88\% on MNMS.

Related papers

• ChorusTIC: Training-Free Multivariate Time Series Classification via Chorus In-Context Learning [52.72143039958434]
  We introduce ChorusTIC, a classification-native foundation model for in-context classification across heterogeneous channel configurations.<n>ChorusTIC maps variable channel configurations into a fixed-width representation independent of the original channel count.<n>It calibrates feature axes using context-derived distributions and predicts query labels through leakage-protected in-context learning.
  arXiv  Detail & Related papers  (2026-08-25T03:45:24Z)
• Compositional Cross-Modality Translation via Whole-Volume Multitask Latent Flow Matching [1.447808799346751]
  Cross-modality medical image translation can reduce the burden of multi-modal acquisitions.<n> Methods operate on 2D slices or 3D patches rather than whole volumes, and train a separate model for each translation task.<n>We propose to decouple these objectives by using a large-scale pretrained 3D variational autoencoder.
  arXiv  Detail & Related papers  (2026-08-08T13:43:23Z)
• DRDN: Decoupled Representation Dynamic Network for From-Scratch ViT Class-Incremental Learning [6.097306160389619]
  Dynamic expansion methods for class-incremental learning (CIL) protect task-specific knowledge by growing dedicated tokens or computationworks.<n>We identify two intertwined challenges: cross-task confusion from sequential training on predominantly current-task data, and under-optimized shared representations in the backbone.<n>We propose the Decoupled Representation Dynamic Network (DRDN), which addresses these challenges via two mechanisms.
  arXiv  Detail & Related papers  (2026-07-02T02:57:58Z)
• Steering Without Breaking: Mechanistically Informed Interventions for Discrete Diffusion Language Models [10.45663857615872]
  Discrete diffusion language models (DLMs) generate text by iteratively denoising all positions in parallel.<n>We show this uniform schedule degrades quality, and the damage compounds when multiple attributes are steered jointly.<n>We propose a novel adaptive scheduler that concentrates interventions on the steps where an attribute is actively forming and leaves the rest of generation untouched.
  arXiv  Detail & Related papers  (2026-05-08T18:52:17Z)
• Posterior Augmented Flow Matching [64.1559809786948]
  Posterior-Augmented Flow Matching (PAFM) is a generalization of flow matching (FM)<n>We show that PAFM improves over FM by up to 3.4 FID50K across different model scales.
  arXiv  Detail & Related papers  (2026-05-01T17:59:59Z)
• Multicentric thrombus segmentation using an attention-based recurrent network with gradual modality dropout [0.0]
  We introduce a methodology that couples an attention-based recurrent segmentation network (UpAttLLSTM)<n>UpAttLLSTM aggregates context across slices via recurrent units (2.5D) and uses attention gates to fuse complementary cues across available sequences.<n>On a monocentric cohort, our approach detects thrombi in >90% of cases with a Dice score of 0.65.<n>In a multi-center setting with missing modalities, it achieves-80% detection with a Dice score around 0.35.
  arXiv  Detail & Related papers  (2026-04-01T12:25:00Z)
• Learning from Many and Adapting to the Unknown in Open-set Test Streams [24.690368986775848]
  Large Language Models (LLMs) generalize across tasks via reusable representations and flexible reasoning.<n>SyCo is a parameter-efficient adaptation method that updates low-rank adapters through Rac1 and MAPK pathways.
  arXiv  Detail & Related papers  (2026-04-01T06:23:24Z)
• Wireless Federated Multi-Task LLM Fine-Tuning via Sparse-and-Orthogonal LoRA [61.12136997430116]
  Decentralized federated learning (DFL) based on low-rank adaptation (LoRA) enables mobile devices with multi-task datasets to collaboratively fine-tune a large language model (LLM) by exchanging locally updated parameters with a subset of neighboring devices via wireless connections for knowledge integration.<n> directly aggregating parameters fine-tuned on heterogeneous datasets induces three primary issues across the DFL life-cycle: (i) catastrophic knowledge forgetting during fine-tuning process, arising from conflicting update directions caused by data heterogeneity; (ii) textitinefficient communication and convergence during model aggregation process,
  arXiv  Detail & Related papers  (2026-02-24T02:45:32Z)
• CoT-Saliency: Unified Chain-of-Thought Reasoning for Heterogeneous Saliency Tasks [96.64597365827046]
  We present the first unified framework that jointly handles three operationally heterogeneous saliency tasks.<n>We introduce a Chain-of-Thought (CoT) reasoning process in a Vision-Language Model (VLM) to bridge task heterogeneity.<n>We show our model matches or outperforms specialized SOTA methods and strong closed-source VLMs across all tasks.
  arXiv  Detail & Related papers  (2025-11-01T04:37:01Z)
• Exploiting Unlabeled Structures through Task Consistency Training for Versatile Medical Image Segmentation [24.25178585285867]
  We introduce a Task Consistency Training (TCT) framework to address class imbalance without requiring extra models.<n>To avoid error propagation from low-consistency, potentially noisy data, we propose a filtering strategy to exclude such data.<n>Experiments on eight abdominal datasets from diverse clinical sites demonstrate our approach's effectiveness.
  arXiv  Detail & Related papers  (2025-09-05T01:04:32Z)
• Semi-supervised Domain Adaptive Structure Learning [72.01544419893628]
  Semi-supervised domain adaptation (SSDA) is a challenging problem requiring methods to overcome both 1) overfitting towards poorly annotated data and 2) distribution shift across domains. We introduce an adaptive structure learning method to regularize the cooperation of SSL and DA.
  arXiv  Detail & Related papers  (2021-12-12T06:11:16Z)
• Decentralized Local Stochastic Extra-Gradient for Variational Inequalities [125.62877849447729]
  We consider distributed variational inequalities (VIs) on domains with the problem data that is heterogeneous (non-IID) and distributed across many devices. We make a very general assumption on the computational network that covers the settings of fully decentralized calculations. We theoretically analyze its convergence rate in the strongly-monotone, monotone, and non-monotone settings.
  arXiv  Detail & Related papers  (2021-06-15T17:45:51Z)
• Learning Task-oriented Disentangled Representations for Unsupervised Domain Adaptation [165.61511788237485]
  Unsupervised domain adaptation (UDA) aims to address the domain-shift problem between a labeled source domain and an unlabeled target domain. We propose a dynamic task-oriented disentangling network (DTDN) to learn disentangled representations in an end-to-end fashion for UDA.
  arXiv  Detail & Related papers  (2020-07-27T01:21:18Z)

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.