Pulling Target to Source: A New Perspective on Domain Adaptive Semantic Segmentation

by   Haochen Wang, et al.
SenseTime Corporation

Domain adaptive semantic segmentation aims to transfer knowledge from a labeled source domain to an unlabeled target domain. However, existing methods primarily focus on directly learning qualified target features, making it challenging to guarantee their discrimination in the absence of target labels. This work provides a new perspective. We observe that the features learned with source data manage to keep categorically discriminative during training, thereby enabling us to implicitly learn adequate target representations by simply pulling target features close to source features for each category. To this end, we propose T2S-DA, which we interpret as a form of pulling Target to Source for Domain Adaptation, encouraging the model in learning similar cross-domain features. Also, considering the pixel categories are heavily imbalanced for segmentation datasets, we come up with a dynamic re-weighting strategy to help the model concentrate on those underperforming classes. Extensive experiments confirm that T2S-DA learns a more discriminative and generalizable representation, significantly surpassing the state-of-the-art. We further show that our method is quite qualified for the domain generalization task, verifying its domain-invariant property.


page 4

page 7

page 17

page 18

page 19


DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation

Unsupervised domain adaptation in semantic segmentation has been raised ...

SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation

Domain adaptive semantic segmentation attempts to make satisfactory dens...

Interventional Domain Adaptation

Domain adaptation (DA) aims to transfer discriminative features learned ...

Generalized Semantic Segmentation by Self-Supervised Source Domain Projection and Multi-Level Contrastive Learning

Deep networks trained on the source domain show degraded performance whe...

Pareto Domain Adaptation

Domain adaptation (DA) attempts to transfer the knowledge from a labeled...

Graph Adaptive Semantic Transfer for Cross-domain Sentiment Classification

Cross-domain sentiment classification (CDSC) aims to use the transferabl...

Towards Fair Knowledge Transfer for Imbalanced Domain Adaptation

Domain adaptation (DA) becomes an up-and-coming technique to address the...

Please sign up or login with your details

Forgot password? Click here to reset