mlsanityData to 14 Oct 2026

Weakly-supervised fire segmentation by visualizing intermediate CNN layers

arXiv 2111.08401 ↗First posted 16 Nov 2021cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Fire localization in images and videos is an important step for an autonomous system to combat fire incidents. State-of-art image segmentation methods based on deep neural networks require a large number of pixel-annotated samples to train Convolutional Neural Networks (CNNs) in a fully-supervised manner. In this paper, we consider weakly supervised segmentation of fire in images, in which only image labels are used to train the network. We show that in the case of fire segmentation, which is a binary segmentation problem, the mean value of features in a mid-layer of classification CNN can perform better than conventional Class Activation Mapping (CAM) method. We also propose to further improve the segmentation accuracy by adding a rotation equivariant regularization loss on the features of the last convolutional layer. Our results show noticeable improvements over baseline method for weakly-supervised fire segmentation.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 29 references that are in the map. First posted on arXiv 16 Nov 2021.

Builds on

18 of 29 references.

References · 18

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  4. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  5. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  6. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  7. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
  8. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  9. 2018Invariant Information Clustering for Unsupervised Image Classification and Segmentationcited by 455
  10. 2016Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learningcited by 441
  11. 2017Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approachcited by 201
  12. 2015Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentationcited by 189
6 more
  1. 2018Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentationcited by 145
  2. 2019Transformation Consistent Self-ensembling Model for Semi-supervised Medical Image Segmentationcited by 140
  3. 2020Evaluating Weakly Supervised Object Localization Methods Rightcited by 105
  4. 2018Learning random-walk label propagation for weakly-supervised semantic segmentationcited by 101
  5. 2015Constrained Convolutional Neural Networks for Weakly Supervised Segmentationcited by 100
  6. 2017Incorporating Network Built-in Priors in Weakly-supervised Semantic Segmentationcited by 3

Built on by

Not cited yet.