D3S2: Diffusion-Guided Dataset Distillation for Semantic Segmentation

• URL: http://arxiv.org/abs/2605.25022v1
• Date: Sun, 24 May 2026 12:01:38 GMT
• Title: D3S2: Diffusion-Guided Dataset Distillation for Semantic Segmentation
• Abstract summary: We identify three key challenges for segmentation DD: (i) long-tailed class imbalance, (ii) the need for strict pixel-wise alignment between images and dense labels, and (iii) the high computational cost of optimizing high-resolution data with complex models.<n>In Class-Balanced Mask Selection, we construct a representative mask set via a greedy strategy that prioritizes underrepresented classes.<n>In Diffusion-Guided Image Synthesis, we employ a pretrained layout-to-image diffusion model to generate images conditioned on the selected masks, naturally ensuring alignment.
• Score: 8.30626759264565
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Dataset distillation (DD) aims to compress large-scale datasets into compact synthetic sets while preserving training efficacy. However, existing studies mainly focus on image classification, leaving dense prediction tasks such as semantic segmentation largely underexplored. In this work, we identify three key challenges for segmentation DD: (i) long-tailed class imbalance, (ii) the need for strict pixel-wise alignment between images and dense labels, and (iii) the high computational cost of optimizing high-resolution data with complex models. To address these challenges, we propose D3S2, a Diffusion-guided Dataset Distillation framework for Semantic Segmentation. Our method adopts a two-stage design. In Class-Balanced Mask Selection, we construct a representative mask set via a greedy strategy that prioritizes underrepresented classes. In Diffusion-Guided Image Synthesis, we employ a pretrained layout-to-image diffusion model to generate images conditioned on the selected masks, naturally ensuring spatial alignment. To further enhance the training utility of synthesized data, we introduce guided diffusion sampling with two complementary objectives: a segmentation-consistency loss for pixel-level alignment, and a class-wise feature matching loss for aligning per-class feature statistics across layers. Extensive experiments demonstrate the superiority of D3S2. Notably, at an extremely compression rate of 1%, our method achieves 24.99% and 35.49% mIoU on ADE20K and COCO-Stuff with Mask2Former (Swin-S), outperforming random selection by 9.34% and 5.70%, respectively.

Related papers

• SAS: Semantic-aware Sampling for Generative Dataset Distillation [55.27114962330541]
  We introduce a semantic-aware perspective for dataset distillation by leveraging Contrastive Language-Image Pretraining (CLIP) as a semantic prior for post-sampling.<n>Our goal is to obtain distilled datasets that are not only compact but also semantically class-discriminative and diverse.
  arXiv  Detail & Related papers  (2026-05-18T08:05:46Z)
• Preference Score Distillation: Leveraging 2D Rewards to Align Text-to-3D Generation with Human Preference [69.34278282513593]
  Preference Score Distillation (PSD) is an optimization-based framework for human-aligned text-to-3D synthesis without 3D training data.<n>Our key insight stems from the incompatibility of pixel-level gradients.<n>We introduce an adaptive strategy to co-optimize preference scores and negative text embeddings.
  arXiv  Detail & Related papers  (2026-03-02T08:23:36Z)
• Dual-Branch Center-Surrounding Contrast: Rethinking Contrastive Learning for 3D Point Clouds [55.5576033344795]
  We propose a novel DualBranch textbfCentertextbfSurrounding textbfContrast (CSCon) framework for 3D point clouds.<n>Under the FULL and ALL protocols, CSCon achieves performance comparable to generative methods.<n>Our method attains state-of-the-art results, even surpassing cross-modal approaches.
  arXiv  Detail & Related papers  (2025-12-09T14:56:35Z)
• Diffusion-Driven Two-Stage Active Learning for Low-Budget Semantic Segmentation [33.970333069082294]
  This paper proposes a novel two-stage selection pipeline for semantic segmentation.<n>We achieve high segmentation accuracy with only a tiny fraction of labeled pixels.<n>Our method significantly outperforms existing baselines under extreme pixel-budget regimes.
  arXiv  Detail & Related papers  (2025-10-25T09:25:01Z)
• Dataset Condensation with Color Compensation [6.704200733185588]
  Existing methods struggle with two: image-level selection methods (Coreset Selection, dataset Quantization) suffer from condensation inefficiency.<n>We find that a critical problem in dataset condensation is the oversight of color's dual role as an information carrier and a basic semantic representation unit.<n>We propose DC3: a dataset condensation framework with Color Compensation.
  arXiv  Detail & Related papers  (2025-08-02T01:44:23Z)
• High-Precision Dichotomous Image Segmentation via Probing Diffusion Capacity [69.32473738284374]
  Diffusion models have revolutionized text-to-image synthesis by delivering exceptional quality, fine detail resolution, and strong contextual awareness.<n>We propose DiffDIS, a diffusion-driven segmentation model that taps into the potential of the pre-trained U-Net within diffusion models.<n>Experiments on the DIS5K dataset demonstrate the superiority of DiffDIS, achieving state-of-the-art results through a streamlined inference process.
  arXiv  Detail & Related papers  (2024-10-14T02:49:23Z)
• Label-Efficient 3D Brain Segmentation via Complementary 2D Diffusion Models with Orthogonal Views [10.944692719150071]
  We propose a novel 3D brain segmentation approach using complementary 2D diffusion models. Our goal is to achieve reliable segmentation quality without requiring complete labels for each individual subject.
  arXiv  Detail & Related papers  (2024-07-17T06:14:53Z)
• Improving Semi-Supervised and Domain-Adaptive Semantic Segmentation with Self-Supervised Depth Estimation [94.16816278191477]
  We present a framework for semi-adaptive and domain-supervised semantic segmentation. It is enhanced by self-supervised monocular depth estimation trained only on unlabeled image sequences. We validate the proposed model on the Cityscapes dataset.
  arXiv  Detail & Related papers  (2021-08-28T01:33:38Z)
• Three Ways to Improve Semantic Segmentation with Self-Supervised Depth Estimation [90.87105131054419]
  We present a framework for semi-supervised semantic segmentation, which is enhanced by self-supervised monocular depth estimation from unlabeled image sequences. We validate the proposed model on the Cityscapes dataset, where all three modules demonstrate significant performance gains.
  arXiv  Detail & Related papers  (2020-12-19T21:18:03Z)
• Scan-based Semantic Segmentation of LiDAR Point Clouds: An Experimental Study [2.6205925938720833]
  State of the art methods use deep neural networks to predict semantic classes for each point in a LiDAR scan. A powerful and efficient way to process LiDAR measurements is to use two-dimensional, image-like projections. We demonstrate various techniques to boost the performance and to improve runtime as well as memory constraints.
  arXiv  Detail & Related papers  (2020-04-06T11:08:12Z)

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.