Skip to Main content Skip to Navigation
Conference papers

Semi-Supervised Semantic Segmentation with Cross-Consistency Training

Abstract : In this paper, we present a novel cross-consistency based semi-supervised approach for semantic segmentation. Consistency training has proven to be a powerful semisupervised learning framework for leveraging unlabeled data under the cluster assumption, in which the decision boundary should lie in low density regions. In this work, we first observe that for semantic segmentation, the low density regions are more apparent within the hidden representations than within the inputs. We thus propose crossconsistency training, where an invariance of the predictions is enforced over different perturbations applied to the outputs of the encoder. Concretely, a shared encoder and a main decoder are trained in a supervised manner using the available labeled examples. To leverage the unlabeled examples, we enforce a consistency between the main decoder predictions and those of the auxiliary decoders, taking as inputs different perturbed versions of the encoder's output, and consequently, improving the encoder's representations. The proposed method is simple and can easily be extended to use additional training signal, such as image-level labels or pixel-level labels across different domains. We perform an ablation study to tease apart the effectiveness of each component, and conduct extensive experiments to demonstrate that our method achieves stateof-the-art results in several datasets.
Document type :
Conference papers
Complete list of metadata
Contributor : Myriam Tami Connect in order to contact the contributor
Submitted on : Thursday, December 10, 2020 - 9:44:05 AM
Last modification on : Tuesday, December 14, 2021 - 3:01:58 AM
Long-term archiving on: : Thursday, March 11, 2021 - 6:48:01 PM


Files produced by the author(s)



yassine Ouali, Céline Hudelot, Myriam Tami. Semi-Supervised Semantic Segmentation with Cross-Consistency Training. CVPR 2020, Jun 2020, Seattle (virtual), United States. ⟨10.1109/CVPR42600.2020.01269⟩. ⟨hal-03049937⟩



Record views


Files downloads