• Corpus ID: 239998188

Inferring the Class Conditional Response Map for Weakly Supervised Semantic Segmentation

@article{Sun2021InferringTC,
  title={Inferring the Class Conditional Response Map for Weakly Supervised Semantic Segmentation},
  author={Weixuan Sun and Jing Zhang and Nick Barnes},
  journal={ArXiv},
  year={2021},
  volume={abs/2110.14309}
}
  • Weixuan Sun, Jing Zhang, N. Barnes
  • Published 27 October 2021
  • Computer Science
  • ArXiv
Image-level weakly supervised semantic segmentation (WSSS) relies on class activation maps (CAMs) for pseudo labels generation. As CAMs only highlight the most discriminative regions of objects, the generated pseudo labels are usually unsatisfactory to serve directly as supervision. To solve this, most existing approaches follow a multitraining pipeline to refine CAMs for better pseudo-labels, which includes: 1) re-training the classification model to generate CAMs; 2) post-processing CAMs to… 
GETAM: Gradient-weighted Element-wise Transformer Attention Map for Weakly-supervised Semantic segmentation
TLDR
This paper proposes the first transformer-based WSSS approach, and introduces the Gradient-weighted Element-wise Transformer Attention Map (GETAM), which shows fine scale activation for all feature map elements, revealing different parts of the object across transformer layers.

References

SHOWING 1-10 OF 54 REFERENCES
Embedded Discriminative Attention Mechanism for Weakly Supervised Semantic Segmentation
  • Tong Wu, Junshi Huang, +4 authors C. Liu
  • Computer Science
    2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2021
TLDR
An Embedded Discriminative Attention Mechanism (EDAM) is proposed by integrating the activation map generation into the classification network directly for WSSS by directly using the activation masks from the DA layer as pseudo-labels for segmentation.
Employing Multi-estimations for Weakly-Supervised Semantic Segmentation
TLDR
This work proposes a novel approach to alleviate the inaccurate seed problem by leveraging the segmentation model’s robustness to learn from multiple seeds.
Reliability Does Matter: An End-to-End Weakly Supervised Semantic Segmentation Approach
TLDR
This work harnesses the image-level labels to produce reliable pixel-level annotations and design a fully end-to-end network to learn to predict segmentation maps and gets a new state-of-the-art performance on the Pascal VOC.
Weakly-Supervised Semantic Segmentation via Sub-Category Exploration
TLDR
This work proposes a simple yet effective approach that introduces a self-supervised task by exploiting the sub- category information and performs clustering on image features to generate pseudo sub-categories labels within each annotated parent class.
Self-Supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation
TLDR
A self-supervised equivariant attention mechanism (SEAM) to discover additional supervision and narrow the gap between full and weak supervisions, and a pixel correlation module (PCM), which exploits context appearance information and refines the prediction of current pixel by its similar neighbors, leading to further improvement on CAMs consistency.
Mixup-CAM: Weakly-supervised Semantic Segmentation via Uncertainty Regularization
TLDR
A principled and end-to-end train-able framework to allow the network to pay attention to other parts of the object, while producing a more complete and uniform response map.
Learning Integral Objects With Intra-Class Discriminator for Weakly-Supervised Semantic Segmentation
TLDR
This paper proposes an efficient end-to-end Intra-Class Discriminator (ICD) framework, which learns intra-class boundaries to help separate the foreground and the background within each image-level class.
Causal Intervention for Weakly-Supervised Semantic Segmentation
TLDR
A structural causal model to analyze the causalities among images, contexts, and class labels is proposed and a new method: Context Adjustment (CONTA) is developed, to remove the confounding bias in image-level classification and thus provide better pseudo-masks as ground-truth for the subsequent segmentation model.
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.
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.
...
1
2
3
4
5
...