High Quality Segmentation for Ultra High-resolution Images

• URL: http://arxiv.org/abs/2111.14482v1
• Date: Mon, 29 Nov 2021 11:53:06 GMT
• Title: High Quality Segmentation for Ultra High-resolution Images
• Authors: Tiancheng Shen, Yuechen Zhang, Lu Qi, Jason Kuen, Xingyu Xie, Jianlong Wu, Zhe Lin, Jiaya Jia
• Abstract summary: We propose the Continuous Refinement Model for the ultra high-resolution segmentation refinement task. Our proposed method is fast and effective on image segmentation refinement.
• Score: 72.97958314291648
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: To segment 4K or 6K ultra high-resolution images needs extra computation consideration in image segmentation. Common strategies, such as down-sampling, patch cropping, and cascade model, cannot address well the balance issue between accuracy and computation cost. Motivated by the fact that humans distinguish among objects continuously from coarse to precise levels, we propose the Continuous Refinement Model~(CRM) for the ultra high-resolution segmentation refinement task. CRM continuously aligns the feature map with the refinement target and aggregates features to reconstruct these images' details. Besides, our CRM shows its significant generalization ability to fill the resolution gap between low-resolution training images and ultra high-resolution testing ones. We present quantitative performance evaluation and visualization to show that our proposed method is fast and effective on image segmentation refinement. Code will be released at https://github.com/dvlab-research/Entity.

Related papers

• HRDecoder: High-Resolution Decoder Network for Fundus Image Lesion Segmentation [12.606794661369959]
  We propose HRDecoder, a simple High-Resolution Decoder network for fundus lesion segmentation. It integrates a high-resolution representation learning module to capture fine-grained local features and a high-resolution fusion module to fuse multi-scale predictions. Our method effectively improves the overall segmentation accuracy of fundus lesions while consuming reasonable memory and computational overhead, and maintaining satisfying inference speed.
  arXiv  Detail & Related papers  (2024-11-06T15:13:31Z)
• High-Precision Dichotomous Image Segmentation via Probing Diffusion Capacity [69.32473738284374]
  We propose DiffDIS, a diffusion-driven segmentation model that taps into the potential of the pre-trained U-Net within diffusion models. By leveraging the robust generalization capabilities and rich, versatile image representation prior to the SD models, we significantly reduce the inference time while preserving high-fidelity, detailed generation. 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)
• Low-Resolution Self-Attention for Semantic Segmentation [96.81482872022237]
  We introduce the Low-Resolution Self-Attention (LRSA) mechanism to capture global context at a significantly reduced computational cost. Our approach involves computing self-attention in a fixed low-resolution space regardless of the input image's resolution. We demonstrate the effectiveness of our LRSA approach by building the LRFormer, a vision transformer with an encoder-decoder structure.
  arXiv  Detail & Related papers  (2023-10-08T06:10:09Z)
• Enhanced Sharp-GAN For Histopathology Image Synthesis [63.845552349914186]
  Histopathology image synthesis aims to address the data shortage issue in training deep learning approaches for accurate cancer detection. We propose a novel approach that enhances the quality of synthetic images by using nuclei topology and contour regularization. The proposed approach outperforms Sharp-GAN in all four image quality metrics on two datasets.
  arXiv  Detail & Related papers  (2023-01-24T17:54:01Z)
• Learning Enriched Features for Fast Image Restoration and Enhancement [166.17296369600774]
  This paper presents a holistic goal of maintaining spatially-precise high-resolution representations through the entire network. We learn an enriched set of features that combines contextual information from multiple scales, while simultaneously preserving the high-resolution spatial details. Our approach achieves state-of-the-art results for a variety of image processing tasks, including defocus deblurring, image denoising, super-resolution, and image enhancement.
  arXiv  Detail & Related papers  (2022-04-19T17:59:45Z)
• Joint Calibrationless Reconstruction and Segmentation of Parallel MRI [21.227526213206545]
  We introduce a novel image domain deep-learning framework for calibrationless parallel MRI reconstruction. The combination of the proposed image domain deep calibrationless approach with the segmentation algorithm offers improved image quality. The proposed few-shot training strategy requires only 10% of segmented datasets to offer good performance.
  arXiv  Detail & Related papers  (2021-05-19T16:04:20Z)
• Foveation for Segmentation of Ultra-High Resolution Images [8.037287701125832]
  We introduce foveation module, a learnable "dataloader" which adaptively chooses the appropriate configuration (FoV/resolution trade-off) of the input patch to feed to the downstream segmentation model. We demonstrate that the foveation module consistently improves segmentation performance over the cases trained with patches of fixed FoV/resolution trade-off.
  arXiv  Detail & Related papers  (2020-07-29T21:44:39Z)
• CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement [0.0]
  State-of-the-art semantic segmentation methods were almost exclusively trained on images within a fixed resolution range. We propose a novel approach to address the high-resolution segmentation problem without using any high-resolution training data.
  arXiv  Detail & Related papers  (2020-05-06T01:38:03Z)
• Learning Enriched Features for Real Image Restoration and Enhancement [166.17296369600774]
  convolutional neural networks (CNNs) have achieved dramatic improvements over conventional approaches for image restoration task. We present a novel architecture with the collective goals of maintaining spatially-precise high-resolution representations through the entire network. Our approach learns an enriched set of features that combines contextual information from multiple scales, while simultaneously preserving the high-resolution spatial details.
  arXiv  Detail & Related papers  (2020-03-15T11:04:30Z)

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.