Modelling Solar Images from Sdo/Aia with Denoising Diffusion Probabilistic Models

Ramunno, Francesco  Pio

doi:10.2139/ssrn.4504193

Cited by 2 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This enables the removal of noise by resampling strategies, greatly reducing sampling steps and accelerating inference speed. Additionally, iDDPM [33] introduces a new noise schedule that has been shown to be more effective than the linear schedule used in DDPM, further shortening sampling steps.…”

Section: Diffusion Modelmentioning

confidence: 99%

Instance-Aware Diffusion Implicit Process for Box-Based Instance Segmentation

Ren,

Liu,

Huang

et al. 2023

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

The diffusion model has demonstrated impressive performance in image generation, but its potential for discriminative tasks such as instance segmentation remains unexplored. In this paper, we propose an Instance-aware Diffusion Implicit Process (IDIP) framework for instance segmentation based on boxes. During training, IDIP diffuses ground-truth boxes across various time steps, extracting corresponding Region of Interest (RoI) features. Dynamic convolution is then used to predict boxes and categories for each RoI, and the mask head generates masks from these predictions. During inference, IDIP iteratively refines randomly generated boxes with the denoising diffusion implicit model, while the mask head derives final masks from RoIs based on the refined boxes. Our method surpasses existing approaches on the COCO benchmark, requiring fewer training steps and less memory resources due to its dynamic design and instance-aware characteristic.

show abstract

Section: Diffusion Modelmentioning

confidence: 99%

Instance-Aware Diffusion Implicit Process for Box-Based Instance Segmentation

Ren,

Liu,

Huang

et al. 2023

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

show abstract

“…Model Architecture Following [39], we employ U-Net for our denoising network. We modify the U-Net to take in 4-channel input (concatenation of image and the corresponding mask m t ) and output a 1-channel refined mask.…”

Section: Implementation Detailsmentioning

confidence: 99%

“…Coarse Mask SegFix [56] MGMatting [55] CascadePSP [12] CRM [44] SegRefiner (ours) FCN-8s [35] 72. 39 Settings In this experiment, we utilize the LR-SegRefiner model. To refine each instance, we extract the bounding box region based on the coarse mask and expand it by 20 pixels on each side.…”

Section: Iou/mbamentioning

confidence: 99%

See 1 more Smart Citation

基于信息传播的动态自相似kc中心网络

Wang

Zhang

Yao

et al. 2022

J. Shanghai Jiaotong Univ. (Sci.)

View full text Add to dashboard Cite

In this paper, we explore a principal way to enhance the quality of object masks produced by different segmentation models. We propose a model-agnostic solution called SegRefiner, which offers a novel perspective on this problem by interpreting segmentation refinement as a data generation process. As a result, the refinement process can be smoothly implemented through a series of denoising diffusion steps. Specifically, SegRefiner takes coarse masks as inputs and refines them using a discrete diffusion process. By predicting the label and corresponding states-transition probabilities for each pixel, SegRefiner progressively refines the noisy masks in a conditional denoising manner. To assess the effectiveness of SegRefiner, we conduct comprehensive experiments on various segmentation tasks, including semantic segmentation, instance segmentation, and dichotomous image segmentation. The results demonstrate the superiority of our SegRefiner from multiple aspects. Firstly, it consistently improves both the segmentation metrics and boundary metrics across different types of coarse masks. Secondly, it outperforms previous model-agnostic refinement methods by a significant margin. Lastly, it exhibits a strong capability to capture extremely fine details when refining high-resolution images. The source code and trained models are available at github.com/MengyuWang826/SegRefiner.

show abstract

Modelling Solar Images from Sdo/Aia with Denoising Diffusion Probabilistic Models

Cited by 2 publications

References 8 publications

Instance-Aware Diffusion Implicit Process for Box-Based Instance Segmentation

Instance-Aware Diffusion Implicit Process for Box-Based Instance Segmentation

基于信息传播的动态自相似kc中心网络

Contact Info

Product

Resources

About