Deep Image Segmentation via Discriminant Feature Learning

• URL: http://arxiv.org/abs/2605.14609v1
• Date: Thu, 14 May 2026 09:25:36 GMT
• Title: Deep Image Segmentation via Discriminant Feature Learning
• Abstract summary: This work introduces Deep Discriminant Analysis (DDA), a differentiable, architecture-agnostic loss function that embeds classical discriminant principles for network training.<n>DDA maximizes between-class variance while minimizing within-class one, promoting compact and separable feature distributions without increasing inference cost.
• Score: 17.344021694835345
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Accurate image segmentation remains challenging, particularly in generating sharp, confident boundaries. While modern architectures have advanced the field, many of them still rely on standard loss functions like Cross-Entropy and Dice, which often neglect the discriminative structure of learned features, leading to inaccurate boundaries. This work introduces Deep Discriminant Analysis (DDA), a differentiable, architecture-agnostic loss function that embeds classical discriminant principles for network training. DDA explicitly maximizes between-class variance while minimizing within-class one, promoting compact and separable feature distributions without increasing inference cost. Evaluations on the DIS5K benchmark demonstrate that DDA consistently improves segmentation accuracy, boundary sharpness, and model confidence across various architectures. Our results show that integrating discriminant analysis offers a simple, effective path for building more robust segmentation models.

Related papers

• Rethinking Vector Field Learning for Generative Segmentation [50.08025820235397]
  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.
  arXiv  Detail & Related papers  (2026-03-19T17:58:19Z)
• The Error of Deep Operator Networks Is the Sum of Its Parts: Branch-Trunk and Mode Error Decompositions [45.88028371034407]
  Operator learning has the potential to strongly impact scientific computing by learning solution operators for differential equations.<n>Despite proven universal approximation properties, deep operator networks (DeepONets) often exhibit limited accuracy and generalization in practice.<n>This work analyzes performance limitations of the classical DeepONet architecture.
  arXiv  Detail & Related papers  (2026-02-25T13:38:08Z)
• A Gift from the Integration of Discriminative and Diffusion-based Generative Learning: Boundary Refinement Remote Sensing Semantic Segmentation [8.690665954055476]
  We propose the Integration of Discriminative and generative learning for Boundary Refinement (IDGBR) framework.<n>The framework first generates a coarse segmentation map using a discriminative backbone model.<n>This map and the original image are fed into a conditioning guidance network to jointly learn a guidance representation.
  arXiv  Detail & Related papers  (2025-07-02T10:47:59Z)
• Approximate Size Targets Are Sufficient for Accurate Semantic Segmentation [52.239136918460616]
  Extending binary class tags to approximate relative object-size distributions allows off-the-shelf architectures to solve the segmentation problem.<n>A straightforward zero-avoiding KL-divergence loss for average predictions produces segmentation accuracy comparable to the standard pixel-precise supervision.<n>Our ideas are validated on PASCAL VOC using our new human annotations of approximate object sizes.
  arXiv  Detail & Related papers  (2025-03-10T06:02:13Z)
• Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection [58.87142367781417]
  A naively trained detector tends to favor overfitting to the limited and monotonous fake patterns, causing the feature space to become highly constrained and low-ranked.<n>One potential remedy is incorporating the pre-trained knowledge within the vision foundation models to expand the feature space.<n>By freezing the principal components and adapting only the remained components, we preserve the pre-trained knowledge while learning fake patterns.
  arXiv  Detail & Related papers  (2024-11-23T19:10:32Z)
• Towards Robust Out-of-Distribution Generalization: Data Augmentation and Neural Architecture Search Approaches [4.577842191730992]
  We study ways toward robust OoD generalization for deep learning. We first propose a novel and effective approach to disentangle the spurious correlation between features that are not essential for recognition. We then study the problem of strengthening neural architecture search in OoD scenarios.
  arXiv  Detail & Related papers  (2024-10-25T20:50:32Z)
• Optimizing against Infeasible Inclusions from Data for Semantic Segmentation through Morphology [58.17907376475596]
  State-of-the-art semantic segmentation models are typically optimized in a data-driven fashion.<n>InSeIn extracts explicit inclusion constraints that govern spatial class relations from the semantic segmentation training set at hand.<n>It then enforces a morphological yet differentiable loss that penalizes violations of these constraints during training to promote prediction feasibility.
  arXiv  Detail & Related papers  (2024-08-26T22:39:08Z)
• One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation [69.65734716679925]
  Knowledge distillation has proven to be a highly effective approach for enhancing model performance through a teacher-student training scheme. Most existing distillation methods are designed under the assumption that the teacher and student models belong to the same model family. We propose a simple yet effective one-for-all KD framework called OFA-KD, which significantly improves the distillation performance between heterogeneous architectures.
  arXiv  Detail & Related papers  (2023-10-30T11:13:02Z)
• Unsupervised Domain Adaptation for Cardiac Segmentation: Towards Structure Mutual Information Maximization [0.8959391124399926]
  Unsupervised domain adaptation approaches have succeeded in various medical image segmentation tasks. UDA-VAE++ is an unsupervised domain adaptation framework for cardiac segmentation with a compact loss function lower bound. Our model outperforms previous state-of-the-art qualitatively and quantitatively.
  arXiv  Detail & Related papers  (2022-04-20T09:10:18Z)
• Self-Ensembling GAN for Cross-Domain Semantic Segmentation [107.27377745720243]
  This paper proposes a self-ensembling generative adversarial network (SE-GAN) exploiting cross-domain data for semantic segmentation. In SE-GAN, a teacher network and a student network constitute a self-ensembling model for generating semantic segmentation maps, which together with a discriminator, forms a GAN. Despite its simplicity, we find SE-GAN can significantly boost the performance of adversarial training and enhance the stability of the model.
  arXiv  Detail & Related papers  (2021-12-15T09:50:25Z)
• 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)
• Lookahead Adversarial Learning for Near Real-Time Semantic Segmentation [2.538209532048867]
  We build a conditional adversarial network with a state-of-the-art segmentation model (DeepLabv3+) at its core. We focus on semantic segmentation models that run fast at inference for near real-time field applications.
  arXiv  Detail & Related papers  (2020-06-19T17:04:38Z)

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.