Rethinking Vector Field Learning for Generative Segmentation

• URL: http://arxiv.org/abs/2603.19218v1
• Date: Thu, 19 Mar 2026 17:58:19 GMT
• Title: Rethinking Vector Field Learning for Generative Segmentation
• Abstract summary: Taming diffusion models for generative segmentation has attracted increasing attention.<n>We revisit diffusion segmentation from the perspective of vector field learning.<n>We propose a principled vector field reshaping strategy that augments the learned vanishing velocity field with a detached distance-aware correction term.<n>This correction introduces both attractive and repulsive interactions, enhancing gradient magnitudes near centroids while preserving the original diffusion training framework.
• Score: 50.08025820235397
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Taming diffusion models for generative segmentation has attracted increasing attention. While existing approaches primarily focus on architectural tweaks or training heuristics, there remains a limited understanding of the intrinsic mismatch between continuous flow matching objectives and discrete perception tasks. In this work, we revisit diffusion segmentation from the perspective of vector field learning. We identify two key limitations of the commonly used flow matching objective: gradient vanishing and trajectory traversing, which result in slow convergence and poor class separation. To tackle these issues, we propose a principled vector field reshaping strategy that augments the learned velocity field with a detached distance-aware correction term. This correction introduces both attractive and repulsive interactions, enhancing gradient magnitudes near centroids while preserving the original diffusion training framework. Furthermore, we design a computationally efficient, quasi-random category encoding scheme inspired by Kronecker sequences, which integrates seamlessly with an end-to-end pixel neural field framework for pixel-level semantic alignment. Extensive experiments consistently demonstrate significant improvements over vanilla flow matching approaches, substantially narrowing the performance gap between generative segmentation and strong discriminative specialists.

Related papers

• One-Step Distillation of Discrete Diffusion Image Generators via Fixed-Point Iteration [20.457786704615454]
  Fixed-Point Distillation (FPD) is an end-to-end framework that constructs local correction targets by partially corrupting the student's one-step draft and refining it with a single teacher step.<n>FPD achieves competitive visual fidelity and structural alignment within a single inference step, narrowing the gap to multi-step teachers.
  arXiv  Detail & Related papers  (2026-05-20T17:59:10Z)
• Making Training-Free Diffusion Segmentors Scale with the Generative Power [118.72472901404814]
  A line of research focuses on adapting a pre-trained diffusion model to semantic segmentation without any further training.<n>We propose two techniques: auto aggregation and per-pixel rescaling, which together enable training-free segmentation to better leverage generative capability.
  arXiv  Detail & Related papers  (2026-03-06T11:35:37Z)
• SPARK: Stochastic Propagation via Affinity-guided Random walK for training-free unsupervised segmentation [18.627047608492795]
  Training-free segmentation methods rely on an implicit and limiting assumption, that segmentation is a spectral graph partitioning problem over diffusion-derived affinities.<n>We introduce a Markov propagation scheme that performs random-walk-based diffusion with an adaptive label pruning strategy.<n>Our method achieves state-of-the-art zero-shot performance, producing sharper boundaries, more coherent regions, and significantly more stable masks compared to prior spectral-clustering-based approaches.
  arXiv  Detail & Related papers  (2026-01-31T05:12:17Z)
• Cluster Purge Loss: Structuring Transformer Embeddings for Equivalent Mutants Detection [0.05461938536945722]
  We introduce a novel framework that integrates cross-entropy loss with a deep metric learning objective, termed Cluster Purge Loss.<n>We demonstrate state-of-the-art performance in the domain of equivalent mutant detection and produce a more interpretable embedding space.
  arXiv  Detail & Related papers  (2025-07-26T23:07:11Z)
• Visual Prompt Tuning in Null Space for Continual Learning [51.96411454304625]
  Existing prompt-tuning methods have demonstrated impressive performances in continual learning (CL) This paper aims to learn each task by tuning the prompts in the direction orthogonal to the subspace spanned by previous tasks' features. In practice, an effective null-space-based approximation solution has been proposed to implement the prompt gradient projection.
  arXiv  Detail & Related papers  (2024-06-09T05:57:40Z)
• Multi-Grained Cross-modal Alignment for Learning Open-vocabulary Semantic Segmentation from Text Supervision [23.931443799102663]
  We introduce a Multi-Grained Cross-modal Alignment (MGCA) framework to bridge the granularity gap without any dense annotations. Specifically, MGCA constructs pseudo multi-granular semantic correspondences upon image-text pairs. Our method achieves significant advancements over state-of-the-art methods, demonstrating its effectiveness and efficiency.
  arXiv  Detail & Related papers  (2024-03-06T13:43:36Z)
• Margin Preserving Self-paced Contrastive Learning Towards Domain Adaptation for Medical Image Segmentation [51.93711960601973]
  We propose a novel margin preserving self-paced contrastive Learning model for cross-modal medical image segmentation. With the guidance of progressively refined semantic prototypes, a novel margin preserving contrastive loss is proposed to boost the discriminability of embedded representation space. Experiments on cross-modal cardiac segmentation tasks demonstrate that MPSCL significantly improves semantic segmentation performance.
  arXiv  Detail & Related papers  (2021-03-15T15:23:10Z)
• Cogradient Descent for Bilinear Optimization [124.45816011848096]
  We introduce a Cogradient Descent algorithm (CoGD) to address the bilinear problem. We solve one variable by considering its coupling relationship with the other, leading to a synchronous gradient descent. Our algorithm is applied to solve problems with one variable under the sparsity constraint.
  arXiv  Detail & Related papers  (2020-06-16T13:41:54Z)
• Contradictory Structure Learning for Semi-supervised Domain Adaptation [67.89665267469053]
  Current adversarial adaptation methods attempt to align the cross-domain features. Two challenges remain unsolved: 1) the conditional distribution mismatch and 2) the bias of the decision boundary towards the source domain. We propose a novel framework for semi-supervised domain adaptation by unifying the learning of opposite structures.
  arXiv  Detail & Related papers  (2020-02-06T22:58:20Z)

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.