Abstract | ||
---|---|---|
Unsupervised domain adaption has proven to be an effective approach for alleviating the intensive workload of manual annotation by aligning the synthetic source-domain data and the real-world target-domain samples. Unfortunately, mapping the target-domain distribution to the source-domain unconditionally may distort the essential structural information of the target-domain data. To this end, we firstly propose to introduce a novel multi-anchor based active learning strategy to assist domain adaptation regarding the semantic segmentation task. By innovatively adopting multiple anchors instead of a single centroid, the source domain can be better characterized as a multimodal distribution, thus more representative and complimentary samples are selected from the target domain. With little workload to manually annotate these active samples, the distortion of the target-domain distribution can be effectively alleviated, resulting in a large performance gain. The multi-anchor strategy is additionally employed to model the target-distribution. By regularizing the latent representation of the target samples compact around multiple anchors through a novel soft alignment loss, more precise segmentation can be achieved. Extensive experiments are conducted on public datasets to demonstrate that the proposed approach outperforms state-of-the-art methods significantly, along with thorough ablation study to verify the effectiveness of each component. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/ICCV48922.2021.00898 | ICCV |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Munan Ning | 1 | 8 | 2.87 |
Donghuan Lu | 2 | 0 | 1.69 |
Dong Wei | 3 | 0 | 1.69 |
Cheng Bian | 4 | 4 | 2.44 |
Chenglang Yuan | 5 | 0 | 2.03 |
Shuang Yu | 6 | 7 | 3.15 |
Kai Ma | 7 | 49 | 18.48 |
Yefeng Zheng | 8 | 1391 | 114.67 |