Intra-class Feature Variation Distillation for Semantic Segmentation

By Yukang Wang, Wei Zhou, Tao Jiang, Xiang Bai, Yongchao Xu. 2020

204 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

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. Chen Qian
2. Fei Wang
3. Elisa Ricci
4. Enrico Fini
5. Moin Nabi
6. Yifan Liu
7. Dan Xu
8. Xavier Alameda-Pineda

In Computer Vision and Pattern Recognition

1. Elisa Ricci
2. Chen Qian
3. Fei Wang
4. Dan Xu
5. Ming Ding
6. Xavier Alameda-Pineda
7. Enrico Fini
8. Yifan Liu

Citations in the corpus

• Uncertainty-aware Contrastive Distillation for Incremental Semantic Segmentation (2022, background): “To the best of our knowledge, the problem of incremental learning in semantic segmentation has been addressed only in [19], [20], [22], [47].”
• Knowledge Distillation from A Stronger Teacher (2022, methodology): “Following [37, 43, 46], we train DeepLabV3 [6] and PSPNet [54] with ResNet-18 backbone on Cityscapes dataset, and adopt our DIST on the predictions of classification head using a teacher with ResNet101 backbone of DeepLabV3.”
• Channel-wise Knowledge Distillation for Dense Prediction* (2020, methodology): “IFVD [34] L2 cos(xi, ∑ j∈Si xj/|Si|) 1×W ×H”