Efficient Domain Generalization via Common-Specific Low-Rank Decomposition

28 Mar 2020Vihari PiratlaPraneeth NetrapalliSunita Sarawagi

Domain generalization refers to the task of training a model which generalizes to new domains that are not seen during training. We present CSD (Common Specific Decomposition), for this setting,which jointly learns a common component (which generalizes to new domains) and a domain specific component (which overfits on training domains)... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Domain Generalization LipitK CSD (Ours) Accuracy 87.3 # 1
Domain Generalization PACS CSD Average Accuracy 80.69 # 4
Domain Generalization Rotated Fashion-MNIST CSD Accuracy 78.9 # 2

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet