Convolution-based Probability Gradient Loss for Semantic Segmentation

• URL: http://arxiv.org/abs/2404.06704v1
• Date: Wed, 10 Apr 2024 03:20:33 GMT
• Title: Convolution-based Probability Gradient Loss for Semantic Segmentation
• Authors: Guohang Shan, Shuangcheng Jia,
• Abstract summary: We introduce a novel Convolution-based Probability Gradient (CPG) loss for semantic segmentation. It employs convolution kernels similar to the Sobel operator, capable of computing the gradient of pixel intensity in an image. We conduct qualitative and quantitative analyses to evaluate the impact of the CPG loss on three well-established networks.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we introduce a novel Convolution-based Probability Gradient (CPG) loss for semantic segmentation. It employs convolution kernels similar to the Sobel operator, capable of computing the gradient of pixel intensity in an image. This enables the computation of gradients for both ground-truth and predicted category-wise probabilities. It enhances network performance by maximizing the similarity between these two probability gradients. Moreover, to specifically enhance accuracy near the object's boundary, we extract the object boundary based on the ground-truth probability gradient and exclusively apply the CPG loss to pixels belonging to boundaries. CPG loss proves to be highly convenient and effective. It establishes pixel relationships through convolution, calculating errors from a distinct dimension compared to pixel-wise loss functions such as cross-entropy loss. We conduct qualitative and quantitative analyses to evaluate the impact of the CPG loss on three well-established networks (DeepLabv3-Resnet50, HRNetV2-OCR, and LRASPP_MobileNet_V3_Large) across three standard segmentation datasets (Cityscapes, COCO-Stuff, ADE20K). Our extensive experimental results consistently and significantly demonstrate that the CPG loss enhances the mean Intersection over Union.

Related papers

• Point Cloud Denoising With Fine-Granularity Dynamic Graph Convolutional Networks [58.050130177241186]
  Noise perturbations often corrupt 3-D point clouds, hindering downstream tasks such as surface reconstruction, rendering, and further processing. This paper introduces finegranularity dynamic graph convolutional networks called GDGCN, a novel approach to denoising in 3-D point clouds.
  arXiv  Detail & Related papers  (2024-11-21T14:19:32Z)
• TransUPR: A Transformer-based Uncertain Point Refiner for LiDAR Point Cloud Semantic Segmentation [6.587305905804226]
  We propose a transformer-based uncertain point refiner, i.e., TransUPR, to refine selected uncertain points in a learnable manner. Our TransUPR achieves state-of-the-art performance, i.e., 68.2% mean Intersection over Union (mIoU) on the Semantic KITTI benchmark.
  arXiv  Detail & Related papers  (2023-02-16T21:38:36Z)
• The KFIoU Loss for Rotated Object Detection [115.334070064346]
  In this paper, we argue that one effective alternative is to devise an approximate loss who can achieve trend-level alignment with SkewIoU loss. Specifically, we model the objects as Gaussian distribution and adopt Kalman filter to inherently mimic the mechanism of SkewIoU. The resulting new loss called KFIoU is easier to implement and works better compared with exact SkewIoU.
  arXiv  Detail & Related papers  (2022-01-29T10:54:57Z)
• Pixel Contrastive-Consistent Semi-Supervised Semantic Segmentation [22.920856071095915]
  We present a novel semi-supervised semantic segmentation method which jointly achieves two desiderata of segmentation model regularities. We leverage the pixel-level L2 loss and the pixel contrastive loss for the two purposes respectively.
  arXiv  Detail & Related papers  (2021-08-20T07:04:33Z)
• PSGR: Pixel-wise Sparse Graph Reasoning for COVID-19 Pneumonia Segmentation in CT Images [83.26057031236965]
  We propose a pixel-wise sparse graph reasoning (PSGR) module to enhance the modeling of long-range dependencies for COVID-19 infected region segmentation in CT images. The PSGR module avoids imprecise pixel-to-node projections and preserves the inherent information of each pixel for global reasoning. The solution has been evaluated against four widely-used segmentation models on three public datasets.
  arXiv  Detail & Related papers  (2021-08-09T04:58:23Z)
• Why Approximate Matrix Square Root Outperforms Accurate SVD in Global Covariance Pooling? [59.820507600960745]
  We propose a new GCP meta-layer that uses SVD in the forward pass, and Pad'e Approximants in the backward propagation to compute the gradients. The proposed meta-layer has been integrated into different CNN models and achieves state-of-the-art performances on both large-scale and fine-grained datasets.
  arXiv  Detail & Related papers  (2021-05-06T08:03:45Z)
• InverseForm: A Loss Function for Structured Boundary-Aware Segmentation [80.39674800972182]
  We present a novel boundary-aware loss term for semantic segmentation using an inverse-transformation network. This plug-in loss term complements the cross-entropy loss in capturing boundary transformations. We analyze the quantitative and qualitative effects of our loss function on three indoor and outdoor segmentation benchmarks.
  arXiv  Detail & Related papers  (2021-04-06T18:52:45Z)
• Improving Image co-segmentation via Deep Metric Learning [1.5076964620370268]
  We propose a novel Triplet loss for Image, called IS-Triplet loss for short, and combine it with traditional image segmentation loss. We apply the proposed approach to image co-segmentation and test it on the SBCoseg dataset and the Internet dataset.
  arXiv  Detail & Related papers  (2021-03-19T07:30:42Z)
• Semi-supervised Hyperspectral Image Classification with Graph Clustering Convolutional Networks [41.78245271989529]
  We propose a graph convolution network (GCN) based framework for HSI classification. In particular, we first cluster the pixels with similar spectral features into a superpixel and build the graph based on the superpixels of the input HSI. We then partition it into several sub-graphs by pruning the edges with weak weights, so as to strengthen the correlations of nodes with high similarity.
  arXiv  Detail & Related papers  (2020-12-20T14:16:59Z)
• Joint Multi-Dimension Pruning via Numerical Gradient Update [120.59697866489668]
  We present joint multi-dimension pruning (abbreviated as JointPruning), an effective method of pruning a network on three crucial aspects: spatial, depth and channel simultaneously. We show that our method is optimized collaboratively across the three dimensions in a single end-to-end training and it is more efficient than the previous exhaustive methods.
  arXiv  Detail & Related papers  (2020-05-18T17:57:09Z)

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.