Larger Norm More Transferable: An Adaptive Feature Norm Approach for Unsupervised Domain Adaptation

Domain adaptation enables the learner to safely generalize into novel environments by mitigating domain shifts across distributions. Previous works may not effectively uncover the underlying reasons that would lead to the drastic model degradation on the target task... (read more)

PDF Abstract ICCV 2019 PDF ICCV 2019 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Domain Adaptation ImageCLEF-DA IAFN+ENT Accuracy 88.9 # 5
Domain Adaptation Office-31 IAFN+ENT Average Accuracy 87.1 # 13
Partial Domain Adaptation Office-Home SAFN Accuracy (%) 71.8 # 6
Domain Adaptation VisDA2017 IAFN Accuracy 76.1 # 10

Methods used in the Paper


METHOD TYPE
Average Pooling
Pooling Operations
Residual Connection
Skip Connections
ReLU
Activation Functions
1x1 Convolution
Convolutions
Batch Normalization
Normalization
Bottleneck Residual Block
Skip Connection Blocks
Global Average Pooling
Pooling Operations
Residual Block
Skip Connection Blocks
Kaiming Initialization
Initialization
Max Pooling
Pooling Operations
Convolution
Convolutions
ResNet
Convolutional Neural Networks