PU-UNet: Stable Multiplicative Interactions for Medical Image Segmentation

• URL: http://arxiv.org/abs/2606.20035v1
• Date: Thu, 18 Jun 2026 10:07:29 GMT
• Title: PU-UNet: Stable Multiplicative Interactions for Medical Image Segmentation
• Abstract summary: Product-Unit U-Net is a residual U-Net that integrates stable product-unit residual blocks into rich low-resolution stages for medical image segmentation.<n>Compared with a matched Residual U-Net baseline, PU-UNet consistently improves Dice and IoU while keeping parameters, FLOPs, and inference nearly unchanged.<n>These results suggest that stable product-unit residual learning can be an effective way to enhance U-Net-style segmentation networks with explicit multiplicative interactions.
• Score: 0.8574682463936006
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Many dense prediction networks rely on additive feature transformations and model higher-order feature interactions only implicitly. Product units provide an explicit mechanism for multiplicative feature modeling, but their logarithmic--exponential formulation can cause numerical instability, which has limited their use in deep dense prediction networks. In this work, we propose Product-Unit U-Net (PU-UNet), a residual U-Net that integrates stable product-unit residual blocks into rich low-resolution stages for medical image segmentation. The proposed formulation combines smooth positivity mapping with log-domain clipping, enabling stable multiplicative feature learning with negligible computational overhead. On ISIC 2018, Kvasir-SEG, and BUSI, PU-UNet achieves Dice scores of 0.942, 0.959, and up to 0.925, respectively. Compared with a matched Residual U-Net baseline, PU-UNet consistently improves Dice and IoU while keeping parameters, FLOPs, and inference latency nearly unchanged, and reduces the image-level false-positive rate on normal BUSI cases from 0.077 to zero. Ablation studies suggest that the gains are associated with product-unit interactions, are strongest under low-resolution placement, and benefit from the proposed stabilization design. These results suggest that stable product-unit residual learning can be an effective way to enhance U-Net-style segmentation networks with explicit multiplicative interactions.

Related papers

• Modeling Nonlinear Feature Interactions with Product-Unit Residual Networks [0.9367224590861915]
  Product-unit residual networks (PURe) integrate multiplicative product units with residual connections to explicitly model cross-feature couplings.<n>We conduct a systematic evaluation on an interaction-driven synthetic benchmark and two real-world datasets.<n> PURe achieves competitive or improved performance, better robustness and sample efficiency in low-data regimes, and enhanced interaction-level interpretability.
  arXiv  Detail & Related papers  (2026-06-05T03:11:08Z)
• Sparse-by-Design Cross-Modality Prediction: L0-Gated Representations for Reliable and Efficient Learning [0.0]
  A unified sparsification primitive would make accuracy-efficiency trade-offs comparable across modalities.<n>We propose a modality-agnostic, feature-wise hard-concrete gating framework that enforces L0-style sparsity directly on learned representations.
  arXiv  Detail & Related papers  (2026-03-26T03:33:42Z)
• Equivariant Evidential Deep Learning for Interatomic Potentials [55.6997213490859]
  Uncertainty quantification is critical for assessing the reliability of machine learning interatomic potentials in molecular dynamics simulations.<n>Existing UQ approaches for MLIPs are often limited by high computational cost or suboptimal performance.<n>We propose textitEquivariant Evidential Deep Learning for Interatomic Potentials ($texte2$IP), a backbone-agnostic framework that models atomic forces and their uncertainty jointly.
  arXiv  Detail & Related papers  (2026-02-11T02:00:25Z)
• Rational ANOVA Networks [12.085684184678348]
  Deep neural networks treat nonlinearities as fixed primitives, limiting both interpretability and control over the induced function class.<n>We propose the Rational-ANOVA Network (RAN), a foundational architecture grounded in functional ANOVA decomposition and Pad-style rational approximation.
  arXiv  Detail & Related papers  (2026-02-03T20:46:00Z)
• Repulsor: Accelerating Generative Modeling with a Contrastive Memory Bank [65.00301565190824]
  mname is a plug-and-play training framework that requires no external encoders.<n>mname achieves a state-of-the-art FID of textbf2.40 within 400k steps, significantly outperforming comparable methods.
  arXiv  Detail & Related papers  (2025-12-09T14:39:26Z)
• Constructive Universal Approximation and Sure Convergence for Multi-Layer Neural Networks [0.0]
  o1Neuro is a new neural network model built on sparse indicator activation neurons.<n>At the population level, a deep o1Neuro can approximate any measurable function of $boldsymbolX$.<n>At the sample level, the optimization of o1Neuro reaches an optimal model with probability approaching one after sufficiently many update rounds.
  arXiv  Detail & Related papers  (2025-07-07T08:55:28Z)
• Robust Fine-tuning of Zero-shot Models via Variance Reduction [56.360865951192324]
  When fine-tuning zero-shot models, our desideratum is for the fine-tuned model to excel in both in-distribution (ID) and out-of-distribution (OOD) We propose a sample-wise ensembling technique that can simultaneously attain the best ID and OOD accuracy without the trade-offs.
  arXiv  Detail & Related papers  (2024-11-11T13:13:39Z)
• SASWISE-UE: Segmentation and Synthesis with Interpretable Scalable Ensembles for Uncertainty Estimation [6.082812294410541]
  This paper introduces an efficient sub-model ensemble framework aimed at enhancing the interpretability of medical deep learning models. By generating uncertainty maps, this framework enables end-users to evaluate the reliability of model outputs.
  arXiv  Detail & Related papers  (2024-11-08T04:37:55Z)
• PseudoNeg-MAE: Self-Supervised Point Cloud Learning using Conditional Pseudo-Negative Embeddings [55.55445978692678]
  PseudoNeg-MAE enhances global feature representation of point cloud masked autoencoders by making them both discriminative and sensitive to transformations.<n>We propose a novel loss that explicitly penalizes invariant collapse, enabling the network to capture richer transformation cues while preserving discriminative representations.
  arXiv  Detail & Related papers  (2024-09-24T07:57:21Z)
• Towards Continual Learning Desiderata via HSIC-Bottleneck Orthogonalization and Equiangular Embedding [55.107555305760954]
  We propose a conceptually simple yet effective method that attributes forgetting to layer-wise parameter overwriting and the resulting decision boundary distortion. Our method achieves competitive accuracy performance, even with absolute superiority of zero exemplar buffer and 1.02x the base model.
  arXiv  Detail & Related papers  (2024-01-17T09:01:29Z)
• Investigating and Improving Latent Density Segmentation Models for Aleatoric Uncertainty Quantification in Medical Imaging [21.311726807879456]
  In image segmentation, latent density models can be utilized to address this problem. The most popular approach is the Probabilistic U-Net (PU-Net), which uses latent Normal densities to optimize the conditional data log-likelihood Evidence Lower Bound. We introduce mutual information updates and entropy-regularized Sinkhorn updates in the latent space to promote homogeneity across all latent dimensions.
  arXiv  Detail & Related papers  (2023-07-31T14:09:03Z)
• Learning Unnormalized Statistical Models via Compositional Optimization [73.30514599338407]
  Noise-contrastive estimation(NCE) has been proposed by formulating the objective as the logistic loss of the real data and the artificial noise. In this paper, we study it a direct approach for optimizing the negative log-likelihood of unnormalized models.
  arXiv  Detail & Related papers  (2023-06-13T01:18:16Z)
• Improving Neural Additive Models with Bayesian Principles [54.29602161803093]
  Neural additive models (NAMs) enhance the transparency of deep neural networks by handling calibrated input features in separate additive sub-networks. We develop Laplace-approximated NAMs (LA-NAMs) which show improved empirical performance on datasets and challenging real-world medical tasks.
  arXiv  Detail & Related papers  (2023-05-26T13:19:15Z)
• NeFT: Negative Feedback Training to Improve Robustness of Compute-In-Memory DNN Accelerators [16.942980574566818]
  We propose Negative Feedback Training (NeFT) to more effectively capture the multi-scale noisy information throughout the network.<n>NeFT outperforms existing state-of-the-art methods with up to a 45.08% improvement in inference accuracy.
  arXiv  Detail & Related papers  (2023-05-23T22:56:26Z)
• Robust Implicit Networks via Non-Euclidean Contractions [63.91638306025768]
  Implicit neural networks show improved accuracy and significant reduction in memory consumption. They can suffer from ill-posedness and convergence instability. This paper provides a new framework to design well-posed and robust implicit neural networks.
  arXiv  Detail & Related papers  (2021-06-06T18:05:02Z)

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.