Structured Consistency Loss for semi-supervised semantic segmentation
By Jongmok Kim, Jooyoung Jang, Hyunwoo Park. 2020
79 citations recorded by the source corpus.
The consistency loss has played a key role in solving problems in recent studies on semi-supervised learning. Yet extant studies with the consistency loss are limited to its application to classification tasks; extant studies on semi-supervised semantic segmentation rely on pixel-wise classification, which does not reflect the structured nature of characteristics in prediction. We propose a structured consistency loss to address this limitation of extant studies. Structured consistency loss promotes consistency in inter-pixel similarity between teacher and student networks. Specifically, collaboration with CutMix optimizes the efficient performance of semi-supervised semantic segmentation with structured consistency loss by reducing computational burden dramatically. The superiority of proposed method is verified with the Cityscapes; The Cityscapes benchmark results with validation and with test data are 81.9 mIoU and 83.84 mIoU respectively. This ranks the first place on the pixel-level semantic labeling task of Cityscapes benchmark suite. To the best of our knowledge, we are the first to present the superiority of state-of-the-art semi-supervised learning in semantic segmentation.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Optimization & Training
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
- Jingdong Wang
- Luc Van Gool
- Yuhui Yuan
- Zizhao Zhang
- Tomas Pfister
- Gang Zeng
- Xiaokang Chen
- Yuliang Zou
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Jingdong Wang
- Dacheng Tao
- Ming-Hsuan Yang
- Yi Yang
- Chen Change Loy
- Trevor Darrell
- Xiaogang Wang
In Optimization & Training
- Xiao Bian
- Lennart Svensson
- Gang Zeng
- Jingdong Wang
- Wilhelm Tranheden
- Tomas Pfister
- Viktor Olsson
- Ping Hu
Citations in the corpus
- ZeroWaste Dataset: Towards Deformable Object Segmentation in Cluttered Scenes (2021, background): “Semi-supervised segmentation methods have been proposed to address such limitations by jointly learning from both annotated and unannotated images [11, 22, 29, 40, 42, 45].”
- DACS: Domain Adaptation via Cross-domain Mixed Sampling (2020, methodology): “For semantic segmentation, existing research in SSL has seen success in enforcing consistency over mixed versions of samples [6, 39].”
- ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning (2020, methodology): “For semantic segmentation, semi-supervised learning has been explored with techniques based on adversarial learning [15, 16], consistency regularization [6, 9, 17, 18], and pseudo-labelling [19, 20].”
- Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision (2021, methodology): “Input perturbation methods [11, 19] augment the input images randomly and impose the consistency constraint between the predictions of augmented images, so that the decision function lies in the low-density region.”
- PseudoSeg: Designing Pseudo Labels for Semantic Segmentation (2020, background): “Consistency regularization based approaches have also been proposed recently, by enforcing the predictions to be consistent, either from augmented input images (French et al., 2020; Kim et al., 2020), perturbed feature embeddings (Ouali et al., 2020), or different networks (Ke et al., 2020).”