Conterfactual Generative Zero-Shot Semantic Segmentation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2021
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909467201765376 |
|---|---|
| author | Shen, Feihong Liu, Jun Hu, Ping |
| author_facet | Shen, Feihong Liu, Jun Hu, Ping |
| contents | zero-shot learning is an essential part of computer vision. As a classical downstream task, zero-shot semantic segmentation has been studied because of its applicant value. One of the popular zero-shot semantic segmentation methods is based on the generative model Most new proposed works added structures on the same architecture to enhance this model. However, we found that, from the view of causal inference, the result of the original model has been influenced by spurious statistical relationships. Thus the performance of the prediction shows severe bias. In this work, we consider counterfactual methods to avoid the confounder in the original model. Based on this method, we proposed a new framework for zero-shot semantic segmentation. Our model is compared with baseline models on two real-world datasets, Pascal-VOC and Pascal-Context. The experiment results show proposed models can surpass previous confounded models and can still make use of additional structures to improve the performance. We also design a simple structure based on Graph Convolutional Networks (GCN) in this work. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2106_06360 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | Conterfactual Generative Zero-Shot Semantic Segmentation Shen, Feihong Liu, Jun Hu, Ping Computer Vision and Pattern Recognition 68T07 I.2.10 zero-shot learning is an essential part of computer vision. As a classical downstream task, zero-shot semantic segmentation has been studied because of its applicant value. One of the popular zero-shot semantic segmentation methods is based on the generative model Most new proposed works added structures on the same architecture to enhance this model. However, we found that, from the view of causal inference, the result of the original model has been influenced by spurious statistical relationships. Thus the performance of the prediction shows severe bias. In this work, we consider counterfactual methods to avoid the confounder in the original model. Based on this method, we proposed a new framework for zero-shot semantic segmentation. Our model is compared with baseline models on two real-world datasets, Pascal-VOC and Pascal-Context. The experiment results show proposed models can surpass previous confounded models and can still make use of additional structures to improve the performance. We also design a simple structure based on Graph Convolutional Networks (GCN) in this work. |
| title | Conterfactual Generative Zero-Shot Semantic Segmentation |
| topic | Computer Vision and Pattern Recognition 68T07 I.2.10 |
| url | https://arxiv.org/abs/2106.06360 |