Single-Stage Semantic Segmentation From Image Labels

@article{Araslanov2020SingleStageSS,
  title={Single-Stage Semantic Segmentation From Image Labels},
  author={Nikita Araslanov and S. Roth},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2020},
  pages={4252-4261}
}
  • Nikita Araslanov, S. Roth
  • Published 2020
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Recent years have seen a rapid growth in new approaches improving the accuracy of semantic segmentation in a weakly supervised setting, i.e. with only image-level labels available for training. However, this has come at the cost of increased model complexity and sophisticated multi-stage training procedures. This is in contrast to earlier work that used only a single stage -- training one segmentation network on image labels -- which was abandoned due to inferior segmentation accuracy. In this… Expand
Towards Single Stage Weakly Supervised Semantic Segmentation
TLDR
This work utilizes point annotations to generate reliable, on-the-fly pseudo-masks through refined and filtered features, and requires point annotations that are only slightly more expensive than image-level annotations, to demonstrate SOTA performance on benchmark datasets, as well as significantly outperform other SOTA WSSS methods on recent real-world datasets. Expand
Class-related graph convolution for weakly supervised semantic segmentation
Semantic segmentation with deep learning has achieved remarkable progress in classifying the pixels in the image. Acquiring sufficient ground-truth supervision to train deep visual models has been aExpand
Learning structure-aware semantic segmentation with image-level supervision
TLDR
This paper argues that the lost structure information in CAM limits its application in downstream semantic segmentation, leading to deteriorated predictions, and introduces an auxiliary semantic boundary detection module, which penalizes the deteriorated predictions. Expand
Weakly-Supervised Image Semantic Segmentation Using Graph Convolutional Networks
TLDR
This work forms the generation of complete pseudo labels as a semi-supervised learning task and learns a 2-layer GCN separately for every training image by back-propagating a Laplacian and an entropy regularization loss. Expand
Adaptive Affinity Loss and Erroneous Pseudo-Label Refinement for Weakly Supervised Semantic Segmentation
  • Xiangrong Zhang, Zelin Peng, +4 authors L. Jiao
  • Computer Science
  • ArXiv
  • 2021
TLDR
This paper introduces an adaptive affinity loss to thoroughly learn the local pairwise affinity of multi-stage approaches in a single-stage model and proposes a novel label reassign loss to mitigate over-fitting. Expand
Complementary Patch for Weakly Supervised Semantic Segmentation
  • Fei Zhang, Chaochen Gu, Chenyue Zhang, Yuchao Dai
  • Computer Science
  • ArXiv
  • 2021
TLDR
A novel Complementary Patch (CP) Representation is proposed and it is proved that the information of the sum of the CAMs by a pair of input images with complementary hidden (patched) parts is greater than or equal to theInformation of the baseline CAM. Expand
Rethinking Interactive Image Segmentation: Feature Space Annotation
TLDR
This work proposes interactive and simultaneous segment annotation from multiple images guided by feature space projection and optimized by metric learning as the labeling progresses, and shows that this approach can surpass the accuracy of state-of-the-art methods in foreground segmentation datasets: iCoSeg, DAVIS, and Rooftop. Expand
Attention-Guided Supervised Contrastive Learning for Semantic Segmentation
TLDR
This paper proposes an attention-guided supervised contrastive learning approach to highlight a single semantic object every time as the target, and proposes a novel two-stage training strategy to achieve such attention. Expand
Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentation
TLDR
A novel framework, namely Explicit Pseudo-pixel Supervision (EPS), which learns from pixel-level feedback by combining two weak supervisions; the image-level label provides the object identity via the localization map and the saliency map from the off-the-shelf saliency detection model offers rich boundaries. Expand
Leveraging Auxiliary Tasks with Affinity Learning for Weakly Supervised Semantic Segmentation
TLDR
This work proposes a novel weakly supervised multi-task framework termed as AuxSegNet, to leverage saliency detection and multi-label image classification as auxiliary tasks to improve the primary task of semantic segmentation using only image-level ground-truth labels. Expand
...
1
2
3
...

References

SHOWING 1-10 OF 67 REFERENCES
Coarse-to-Fine Semantic Segmentation From Image-Level Labels
TLDR
This paper proposes a novel recursive coarse-to-fine semantic segmentation framework based on only image-level category labels that can be easily extended to foreground object segmentation task and achieves comparable performance with the state-of-the-art supervised methods on the Internet object dataset. Expand
Exploiting Saliency for Object Segmentation from Image Level Labels
TLDR
This paper proposes using a saliency model as additional information and hereby exploit prior knowledge on the object extent and image statistics and shows how to combine both information sources in order to recover 80% of the fully supervised performance of pixel-wise semantic labelling. Expand
STC: A Simple to Complex Framework for Weakly-Supervised Semantic Segmentation
TLDR
A simple to complex (STC) framework in which only image-level annotations are utilized to learn DCNNs for semantic segmentation, which demonstrates the superiority of the proposed STC framework compared with other state-of-the-arts frameworks. Expand
Learning Pixel-Level Semantic Affinity with Image-Level Supervision for Weakly Supervised Semantic Segmentation
  • Jiwoon Ahn, Suha Kwak
  • Computer Science
  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
TLDR
On the PASCAL VOC 2012 dataset, a DNN learned with segmentation labels generated by the method outperforms previous models trained with the same level of supervision, and is even as competitive as those relying on stronger supervision. Expand
From image-level to pixel-level labeling with Convolutional Networks
TLDR
A Convolutional Neural Network-based model is proposed, which is constrained during training to put more weight on pixels which are important for classifying the image, and which beats the state of the art results in weakly supervised object segmentation task by a large margin. Expand
Weakly-and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation
TLDR
Expectation-Maximization (EM) methods for semantic image segmentation model training under weakly supervised and semi-supervised settings are developed and extensive experimental evaluation shows that the proposed techniques can learn models delivering competitive results on the challenging PASCAL VOC 2012 image segmentsation benchmark, while requiring significantly less annotation effort. Expand
Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Features
TLDR
An iterative bottom-up and top-down framework which alternatively expands object regions and optimizes segmentation network and outperforms previous state-of-the-art methods by a large margin is proposed. Expand
Weakly-Supervised Semantic Segmentation Network with Deep Seeded Region Growing
TLDR
This paper proposes to train a semantic segmentation network starting from the discriminative regions and progressively increase the pixel-level supervision using by seeded region growing, and obtains the state-of-the-art performance. Expand
Combining Bottom-Up, Top-Down, and Smoothness Cues for Weakly Supervised Image Segmentation
  • A. Roy, S. Todorovic
  • Computer Science
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
TLDR
This paper addresses the problem of weakly supervised semantic image segmentation with a novel deep architecture which fuses three distinct computation processes toward semantic segmentation &#x2013 and formulate a unified end-to-end learning of all components of the deep architecture. Expand
Self-Supervised Difference Detection for Weakly-Supervised Semantic Segmentation
TLDR
This paper proposes the self-supervised difference detection module, which estimates noise from the results of the mapping functions by predicting the difference between the segmentation masks before and after the mapping, and improves the accuracy by removing noise. Expand
...
1
2
3
4
5
...