Conterfactual Generative Zero-Shot Semantic Segmentation

By Feihong Shen, Jun Liu, Ping Hu. 2021

11 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Nan Shao
2. Yujun Chen
3. Yulun Du
4. Dengxin Dai
5. Jian Ding
6. Zhilin Yang
7. Haiyu Li
8. Hanwei Xu

In Computer Vision and Pattern Recognition

1. Guisong Xia
2. Jian Ding
3. Nan Xue
4. Dengxin Dai
5. Nan Shao
6. Yulun Du
7. Zhilin Yang
8. Luc Van Gool

In Generative Models

1. Dengxin Dai
2. Zhilin Yang

Citations in the corpus

• ZeroPrompt: Scaling Prompt-Based Pretraining to 1, 000 Tasks Improves Zero-Shot Generalization (2022, background): “, 2021; Schick and Schütze, 2021), or even without any training sample (Shen et al., 2021; Sanh et al., 2021).”
• Decoupling Zero-Shot Semantic Segmentation (2021, methodology): “The later works [20, 21, 29, 31, 49, 51] all follow this formulation to address different issues in ZS3.”