# A Gift from the Integration of Discriminative and Diffusion-based Generative Learning: Boundary Refinement Remote Sensing Semantic Segmentation

arXiv: https://arxiv.org/abs/2507.01573 · HTML: https://mlsanity.com/paper/2507.01573/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- Builds on 34 of its 61 references that are in the map.
- First posted on arXiv 2 Jul 2025.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Builds on (most cited first, 30 of 34)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2012.15840/) (2020)
- [Segmenter: Transformer for Semantic Segmentation](https://mlsanity.com/paper/2105.05633/) (2021)
- [Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think](https://mlsanity.com/paper/2410.06940/) (2024)
- [Label-Efficient Semantic Segmentation with Diffusion Models](https://mlsanity.com/paper/2112.03126/) (2021)
- [PointRend: Image Segmentation as Rendering](https://mlsanity.com/paper/1912.08193/) (2019)
- [Unleashing Text-to-Image Diffusion Models for Visual Perception](https://mlsanity.com/paper/2303.02153/) (2023)
- [FreeU: Free Lunch in Diffusion U-Net](https://mlsanity.com/paper/2309.11497/) (2023)
- [UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagery](https://mlsanity.com/paper/2109.08937/) (2021)
- [Gated-SCNN: Gated Shape CNNs for Semantic Segmentation](https://mlsanity.com/paper/1907.05740/) (2019)
- [DDP: Diffusion Model for Dense Visual Prediction](https://mlsanity.com/paper/2303.17559/) (2023)
- [Disentangled Non-Local Neural Networks](https://mlsanity.com/paper/2006.06668/) (2020)
- [DiffusionSat: A Generative Foundation Model for Satellite Imagery](https://mlsanity.com/paper/2312.03606/) (2023)
- [Diffusion Probabilistic Model Made Slim](https://mlsanity.com/paper/2211.17106/) (2022)
- [Boundary-Aware Feature Propagation for Scene Segmentation](https://mlsanity.com/paper/1909.00179/) (2019)
- [On the Frequency Bias of Generative Models](https://mlsanity.com/paper/2111.02447/) (2021)
- [Text2Earth: Unlocking Text-driven Remote Sensing Image Generation with a Global-Scale Dataset and a Foundation Model](https://mlsanity.com/paper/2501.00895/) (2025)
- [LSKNet: A Foundation Lightweight Backbone for Remote Sensing](https://mlsanity.com/paper/2403.11735/) (2024)
- [MetaEarth: A Generative Foundation Model for Global-Scale Remote Sensing Image Generation](https://mlsanity.com/paper/2405.13570/) (2024)
- [Classification With an Edge: Improving Semantic Image Segmentation with Boundary Detection](https://mlsanity.com/paper/1612.01337/) (2016)
- [COMPOSE: Cross-Modal Pseudo-Siamese Network for Patient Trial Matching](https://mlsanity.com/paper/2006.08765/) (2020)
- [Convolutional Random Walk Networks for Semantic Image Segmentation](https://mlsanity.com/paper/1605.07681/) (2016)
- [Building Bridges across Spatial and Temporal Resolutions: Reference-Based Super-Resolution via Change Priors and Conditional Diffusion Model](https://mlsanity.com/paper/2403.17460/) (2024)

## Built on by (most cited first, 1 of 1)

- [Robust Multispectral Semantic Segmentation under Missing or Full Modalities via Structured Latent Projection](https://mlsanity.com/paper/2604.15856/) (2026)

## Abstract (arXiv)

Remote sensing semantic segmentation must address both what the ground objects are within an image and where they are located. Consequently, segmentation models must ensure not only the semantic correctness of large-scale patches (low-frequency information) but also the precise localization of boundaries between patches (high-frequency information). However, most existing approaches rely heavily on discriminative learning, which excels at capturing low-frequency features, while overlooking its inherent limitations in learning high-frequency features for semantic segmentation. Recent studies have revealed that diffusion generative models excel at generating high-frequency details. Our theoretical analysis confirms that the diffusion denoising process significantly enhances the model's ability to learn high-frequency features; however, we also observe that these models exhibit insufficient semantic inference for low-frequency features when guided solely by the original image. Therefore, we integrate the strengths of both discriminative and generative learning, proposing the Integration of Discriminative and diffusion-based Generative learning for Boundary Refinement (IDGBR) framework. The framework first generates a coarse segmentation map using a discriminative backbone model. This map and the original image are fed into a conditioning guidance network to jointly learn a guidance representation subsequently leveraged by an iterative denoising diffusion process refining the coarse segmentation. Extensive experiments across five remote sensing semantic segmentation datasets (binary and multi-class segmentation) confirm our framework's capability of consistent boundary refinement for coarse results from diverse discriminative architectures.