Unsupervised Domain Adaptation in Semantic Segmentation via Orthogonal and Clustered Embeddings
By Marco Toldo, Umberto Michieli, Pietro Zanuttigh. 2020
48 citations recorded by the source corpus.
Deep learning frameworks allowed for a remarkable advancement in semantic segmentation, but the data hungry nature of convolutional networks has rapidly raised the demand for adaptation techniques able to transfer learned knowledge from label-abundant domains to unlabeled ones. In this paper we propose an effective Unsupervised Domain Adaptation (UDA) strategy, based on a feature clustering method that captures the different semantic modes of the feature distribution and groups features of the same class into tight and well-separated clusters. Furthermore, we introduce two novel learning objectives to enhance the discriminative clustering performance: an orthogonality loss forces spaced out individual representations to be orthogonal, while a sparsity loss reduces class-wise the number of active feature channels. The joint effect of these modules is to regularize the structure of the feature space. Extensive evaluations in the synthetic-to-real scenario show that we achieve state-of-the-art performance.
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
- Pietro Zanuttigh
- Umberto Michieli
- Fabio Cermelli
- Arthur Douillard
- Matthieu Cord
- Barbara Caputo
- Brahim Chaib-draa
- Mathieu Pagé Fortin
In Computer Vision and Pattern Recognition
- Umberto Michieli
- Pietro Zanuttigh
- Fabio Cermelli
- Arthur Douillard
- Matthieu Cord
- Barbara Caputo
- Brahim Chaib-draa
- Mathieu Pagé Fortin
Citations in the corpus
- Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations (2021, methodology): “also recalls features clustering (if features belong to the same class) and separation (if features belong to different classes), which has been recently applied to adapt semantic segmentation models across domains [29, 37, 61].”