Towards Interpretable Semantic Segmentation via Gradient-weighted Class Activation Mapping

• URL: http://arxiv.org/abs/2002.11434v1
• Date: Wed, 26 Feb 2020 12:32:40 GMT
• Title: Towards Interpretable Semantic Segmentation via Gradient-weighted Class Activation Mapping
• Authors: Kira Vinogradova, Alexandr Dibrov, Gene Myers
• Abstract summary: We propose SEG-GRAD-CAM, a gradient-based method for interpreting semantic segmentation. Our method is an extension of the widely-used Grad-CAM method, applied locally to produce heatmaps showing the relevance of individual pixels for semantic segmentation.
• Score: 71.91734471596432
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Convolutional neural networks have become state-of-the-art in a wide range of image recognition tasks. The interpretation of their predictions, however, is an active area of research. Whereas various interpretation methods have been suggested for image classification, the interpretation of image segmentation still remains largely unexplored. To that end, we propose SEG-GRAD-CAM, a gradient-based method for interpreting semantic segmentation. Our method is an extension of the widely-used Grad-CAM method, applied locally to produce heatmaps showing the relevance of individual pixels for semantic segmentation.

Related papers

• Leveraging CAM Algorithms for Explaining Medical Semantic Segmentation [4.818865062632567]
  Convolutional neural networks (CNNs) achieve prevailing results in segmentation tasks nowadays. One way of interpreting a CNN is the use of class activation maps (CAMs) that represent heatmaps. We propose a transfer between existing classification- and segmentation-based methods for more detailed, explainable, and consistent results.
  arXiv  Detail & Related papers  (2024-09-30T13:43:00Z)
• Semi-Supervised Semantic Segmentation Based on Pseudo-Labels: A Survey [49.47197748663787]
  This review aims to provide a first comprehensive and organized overview of the state-of-the-art research results on pseudo-label methods in the field of semi-supervised semantic segmentation. In addition, we explore the application of pseudo-label technology in medical and remote-sensing image segmentation.
  arXiv  Detail & Related papers  (2024-03-04T10:18:38Z)
• Transforming gradient-based techniques into interpretable methods [3.6763102409647526]
  We introduce GAD (Gradient Artificial Distancing) as a supportive framework for gradient-based techniques. Its primary objective is to accentuate influential regions by establishing distinctions between classes. Empirical investigations involving occluded images have demonstrated that the identified regions through this methodology indeed play a pivotal role in facilitating class differentiation.
  arXiv  Detail & Related papers  (2024-01-25T09:24:19Z)
• EmerDiff: Emerging Pixel-level Semantic Knowledge in Diffusion Models [52.3015009878545]
  We develop an image segmentor capable of generating fine-grained segmentation maps without any additional training. Our framework identifies semantic correspondences between image pixels and spatial locations of low-dimensional feature maps. In extensive experiments, the produced segmentation maps are demonstrated to be well delineated and capture detailed parts of the images.
  arXiv  Detail & Related papers  (2024-01-22T07:34:06Z)
• Unsupervised Domain Adaptation for Semantic Segmentation using One-shot Image-to-Image Translation via Latent Representation Mixing [9.118706387430883]
  We propose a new unsupervised domain adaptation method for the semantic segmentation of very high resolution images. An image-to-image translation paradigm is proposed, based on an encoder-decoder principle where latent content representations are mixed across domains. Cross-city comparative experiments have shown that the proposed method outperforms state-of-the-art domain adaptation methods.
  arXiv  Detail & Related papers  (2022-12-07T18:16:17Z)
• Weakly-supervised segmentation of referring expressions [81.73850439141374]
  Text grounded semantic SEGmentation learns segmentation masks directly from image-level referring expressions without pixel-level annotations. Our approach demonstrates promising results for weakly-supervised referring expression segmentation on the PhraseCut and RefCOCO datasets.
  arXiv  Detail & Related papers  (2022-05-10T07:52:24Z)
• Uncertainty-Based Dynamic Graph Neighborhoods For Medical Segmentation [0.0]
  Post-processing and refining the results of segmentation is a common practice to decrease the misclassifications originating from the segmentation network. A graph-based approach makes use of certain and uncertain points in a graph and refines the segmentation according to a small graph convolutional network (GCN) We propose a new neighbor-selection mechanism according to feature distances and combine the two networks in the training procedure.
  arXiv  Detail & Related papers  (2021-08-06T13:39:35Z)
• Semantic Distribution-aware Contrastive Adaptation for Semantic Segmentation [50.621269117524925]
  Domain adaptive semantic segmentation refers to making predictions on a certain target domain with only annotations of a specific source domain. We present a semantic distribution-aware contrastive adaptation algorithm that enables pixel-wise representation alignment. We evaluate SDCA on multiple benchmarks, achieving considerable improvements over existing algorithms.
  arXiv  Detail & Related papers  (2021-05-11T13:21:25Z)
• Rethinking Interactive Image Segmentation: Feature Space Annotation [68.8204255655161]
  We propose interactive and simultaneous segment annotation from multiple images guided by feature space projection. We show that our approach can surpass the accuracy of state-of-the-art methods in foreground segmentation datasets.
  arXiv  Detail & Related papers  (2021-01-12T10:13:35Z)

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.