Union-Set Multi-source Model Adaptation for Semantic Segmentation

Li, Zongyao; Togo, Ren; Ogawa, Takahiro; Haseyama, Miki

doi:10.1007/978-3-031-19818-2_33

Cited by 5 publications

(3 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To verify the effectiveness of the proposed MS-CADA method, four conventional single-source UDA methods including Li's [57], DAFormer [56], HRDA [58] and PCEL [55], and four multi-source UDA methods including UMMA [41], DCTN [36], He's [32] and MECKA [40], are used for performance comparison.…”

Section: Methods and Measures For Comparisonmentioning

confidence: 99%

“…Lu et al and Gong et al introduce IDA into the remote sensing field and preliminarily explore the performance of RSIs cross-domain scene classification [38], [39], and Ngo et al further deepen the research on this issue [40]. In addition, Li et al propose to conduct the class-incomplete model adaptation without accessing source information, and design a deep model for street scene semantic segmentation [41]. However, the performance of this method on target domain is dissatisfactory, since it abandons the source knowledge in the domain adaptation process.…”

Section: Incomplete and Partial Domain Adaptationmentioning

confidence: 99%

“…summed at the element level, and then the pseudo-labels are obtained through the softmax activation. The Ensemble method comes from the research of Li et al[41], and actually performs the selective average calculation on different results. Through comparison, it is found that the self-supervised training with only the results of one source expert will produce the suboptimal performance.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Learning General-Purpose Representations for Cross-Domain Hyperspectral Images Classification with Small Samples

Gao

Xiong

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Cross-domain classification with small samples is a more challenging and realistic experimental setup. Until now, few studies have focused on the problem of small-sample cross-domain classification between completely different hyperspectral images (HSIs) since they possess different land cover types and statistical characteristics. To this end, this paper proposes a general-purpose representation learning method for cross-domain HSI classification, aiming to enable the model to learn more general-purpose deep representations that can quickly adapt to different target domains with small samples. The core of this method is to propose a novel three-level distillation strategy to transfer knowledge from multiple models well-trained on source HSIs into a single distilled model at the channel-, feature- and logit-level simultaneously. The learned representations can be further fine-tuned with small samples and quickly adapt to new target HSIs and previously unseen classes. Specifically, to transfer and fuse knowledge from multiple-source domains into a single model simultaneously and solve the inconsistency of the number of bands in different HSIs, an extensible multi-task model, including the channel transformation module, the feature extraction module and the linear classification module, is designed. Only the feature extraction module is shared across different HSIs, while the other two modules are domain-specific. Furthermore, the typical episode-based learning strategy of the metric-based meta-learning is adopted in the whole learning process to further improve the generalization ability and data efficiency. Extensive experiments are conducted on six source HSIs and four target HSIs, and the results demonstrate that the proposed method outperforms the existing advanced methods in cross-domain HSI classification with small samples.

show abstract