MAGIC-Flow: Multiscale Adaptive Conditional Flows for Generation and Interpretable Classification

• URL: http://arxiv.org/abs/2510.22070v1
• Date: Fri, 24 Oct 2025 23:11:25 GMT
• Title: MAGIC-Flow: Multiscale Adaptive Conditional Flows for Generation and Interpretable Classification
• Authors: Luca Caldera, Giacomo Bottacini, Lara Cavinato,
• Abstract summary: MAGIC-Flow is a conditional multiscale normalizing flow architecture that performs generation and classification within a single framework.<n>We show how this ensures exact likelihood and stable optimization, while invertibility enables explicit visualization of sample likelihoods.<n>We evaluate MAGIC-Flow against top baselines using metrics for similarity, fidelity, and diversity.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Generative modeling has emerged as a powerful paradigm for representation learning, but its direct applicability to challenging fields like medical imaging remains limited: mere generation, without task alignment, fails to provide a robust foundation for clinical use. We propose MAGIC-Flow, a conditional multiscale normalizing flow architecture that performs generation and classification within a single modular framework. The model is built as a hierarchy of invertible and differentiable bijections, where the Jacobian determinant factorizes across sub-transformations. We show how this ensures exact likelihood computation and stable optimization, while invertibility enables explicit visualization of sample likelihoods, providing an interpretable lens into the model's reasoning. By conditioning on class labels, MAGIC-Flow supports controllable sample synthesis and principled class-probability estimation, effectively aiding both generative and discriminative objectives. We evaluate MAGIC-Flow against top baselines using metrics for similarity, fidelity, and diversity. Across multiple datasets, it addresses generation and classification under scanner noise, and modality-specific synthesis and identification. Results show MAGIC-Flow creates realistic, diverse samples and improves classification. MAGIC-Flow is an effective strategy for generation and classification in data-limited domains, with direct benefits for privacy-preserving augmentation, robust generalization, and trustworthy medical AI.

Related papers

• LeMoF: Level-guided Multimodal Fusion for Heterogeneous Clinical Data [8.518374850545912]
  Level-guided Modal Fusion (LeMoF) is a novel framework that selectively integrates level-guided representations within each modality.<n>LeMoF explicitly separates and learns global modality-level predictions from level-specific discriminative representations.<n> Experiments on length of stay prediction using Intensive Care Unit (ICU) data demonstrate that LeMoF consistently outperforms existing state-of-the-art multimodal fusion techniques.
  arXiv  Detail & Related papers  (2026-01-15T05:44:05Z)
• FLsim: A Modular and Library-Agnostic Simulation Framework for Federated Learning [3.62218729239779]
  Federated Learning (FL) has undergone significant development since its inception in 2016.<n>We introduce FLsim, a comprehensive FL simulation framework designed to meet the diverse requirements of FL in the literature.<n>We demonstrate the effectiveness and versatility of FLsim in a diverse range of state-of-the-art FL experiments.
  arXiv  Detail & Related papers  (2025-07-15T15:53:01Z)
• Symmetrical Flow Matching: Unified Image Generation, Segmentation, and Classification with Score-Based Generative Models [7.561148568365396]
  Flow Matching has emerged as a powerful framework for learning continuous transformations between distributions.<n>This work introduces Symmetrical Flow Matching, a new formulation that unifies semantic segmentation, classification, and image generation within a single model.<n>It achieves state-of-the-art performance on semantic image synthesis, obtaining FID scores of 11.9 on CelebAMask-HQ and 7.0 on COCO-Stuff with only 25 inference steps.
  arXiv  Detail & Related papers  (2025-06-12T12:19:28Z)
• Exploring Beyond Logits: Hierarchical Dynamic Labeling Based on Embeddings for Semi-Supervised Classification [49.09505771145326]
  We propose a Hierarchical Dynamic Labeling (HDL) algorithm that does not depend on model predictions and utilizes image embeddings to generate sample labels. Our approach has the potential to change the paradigm of pseudo-label generation in semi-supervised learning.
  arXiv  Detail & Related papers  (2024-04-26T06:00:27Z)
• Variational Classification [51.2541371924591]
  We derive a variational objective to train the model, analogous to the evidence lower bound (ELBO) used to train variational auto-encoders. Treating inputs to the softmax layer as samples of a latent variable, our abstracted perspective reveals a potential inconsistency. We induce a chosen latent distribution, instead of the implicit assumption found in a standard softmax layer.
  arXiv  Detail & Related papers  (2023-05-17T17:47:19Z)
• GSMFlow: Generation Shifts Mitigating Flow for Generalized Zero-Shot Learning [55.79997930181418]
  Generalized Zero-Shot Learning aims to recognize images from both the seen and unseen classes by transferring semantic knowledge from seen to unseen classes. It is a promising solution to take the advantage of generative models to hallucinate realistic unseen samples based on the knowledge learned from the seen classes. We propose a novel flow-based generative framework that consists of multiple conditional affine coupling layers for learning unseen data generation.
  arXiv  Detail & Related papers  (2022-07-05T04:04:37Z)
• Mitigating Generation Shifts for Generalized Zero-Shot Learning [52.98182124310114]
  Generalized Zero-Shot Learning (GZSL) is the task of leveraging semantic information (e.g., attributes) to recognize the seen and unseen samples, where unseen classes are not observable during training. We propose a novel Generation Shifts Mitigating Flow framework for learning unseen data synthesis efficiently and effectively. Experimental results demonstrate that GSMFlow achieves state-of-the-art recognition performance in both conventional and generalized zero-shot settings.
  arXiv  Detail & Related papers  (2021-07-07T11:43:59Z)
• GLOWin: A Flow-based Invertible Generative Framework for Learning Disentangled Feature Representations in Medical Images [40.58581577183134]
  Flow-based generative models have been proposed to generate realistic images by directly modeling the data distribution with invertible functions. We propose a new flow-based generative model framework, named GLOWin, that is end-to-end invertible and able to learn disentangled representations.
  arXiv  Detail & Related papers  (2021-03-19T15:47:01Z)
• Autoregressive Score Matching [113.4502004812927]
  We propose autoregressive conditional score models (AR-CSM) where we parameterize the joint distribution in terms of the derivatives of univariable log-conditionals (scores) For AR-CSM models, this divergence between data and model distributions can be computed and optimized efficiently, requiring no expensive sampling or adversarial training. We show with extensive experimental results that it can be applied to density estimation on synthetic data, image generation, image denoising, and training latent variable models with implicit encoders.
  arXiv  Detail & Related papers  (2020-10-24T07:01:24Z)
• Uncertainty quantification in medical image segmentation with normalizing flows [0.9176056742068811]
  We propose a novel conditional generative model that is based on conditional Normalizing Flow (cFlow) The basic idea is to increase the expressivity of the cVAE by introducing a cFlow transformation step after the encoder. This yields improved approximations of the latent posterior distribution, allowing the model to capture richer segmentation variations.
  arXiv  Detail & Related papers  (2020-06-04T07:56:46Z)
• Semi-Supervised Learning with Normalizing Flows [54.376602201489995]
  FlowGMM is an end-to-end approach to generative semi supervised learning with normalizing flows. We show promising results on a wide range of applications, including AG-News and Yahoo Answers text data.
  arXiv  Detail & Related papers  (2019-12-30T17:36:33Z)

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.