The reviewed record of science sign in
Pith

arxiv: 2112.02359 · v1 · pith:BCDNWHXW · submitted 2021-12-04 · cs.CV

Unsupervised Adaptation of Semantic Segmentation Models without Source Data

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:BCDNWHXWrecord.jsonopen to challenge →

classification cs.CV
keywords sourcedatatargetadaptationmodelonlyunlabeledunsupervised
0
0 comments X
read the original abstract

We consider the novel problem of unsupervised domain adaptation of source models, without access to the source data for semantic segmentation. Unsupervised domain adaptation aims to adapt a model learned on the labeled source data, to a new unlabeled target dataset. Existing methods assume that the source data is available along with the target data during adaptation. However, in practical scenarios, we may only have access to the source model and the unlabeled target data, but not the labeled source, due to reasons such as privacy, storage, etc. In this work, we propose a self-training approach to extract the knowledge from the source model. To compensate for the distribution shift from source to target, we first update only the normalization parameters of the network with the unlabeled target data. Then we employ confidence-filtered pseudo labeling and enforce consistencies against certain transformations. Despite being very simple and intuitive, our framework is able to achieve significant performance gains compared to directly applying the source model on the target data as reflected in our extensive experiments and ablation studies. In fact, the performance is just a few points away from the recent state-of-the-art methods which use source data for adaptation. We further demonstrate the generalisability of the proposed approach for fully test-time adaptation setting, where we do not need any target training data and adapt only during test-time.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.