Domain-Specific Batch Normalization for Unsupervised Domain Adaptation

By Woonggi Chang, Tackgeun You, Seonguk Seo, Suha Kwak, Bohyung Han. Computer Vision and Pattern Recognition, 2019

435 citations recorded by the source corpus.

We propose a novel unsupervised domain adaptation framework based on domain-specific batch normalization in deep neural networks. We aim to adapt to both domains by specializing batch normalization layers in convolutional neural networks while allowing them to share all other model parameters, which is realized by a two-stage algorithm. In the first stage, we estimate pseudo-labels for the examples in the target domain using an external unsupervised domain adaptation algorithm---for example, MSTN or CPUA---integrating the proposed domain-specific batch normalization. The second stage learns the final models using a multi-task classification loss for the source and target domains. Note that the two domains have separate batch normalization layers in both stages. Our framework can be easily incorporated into the domain adaptation techniques based on deep neural networks with batch normalization layers. We also present that our approach can be extended to the problem with multiple source domains. The proposed algorithm is evaluated on multiple benchmark datasets and achieves the state-of-the-art accuracy in the standard setting and the multi-source domain adaption scenario.

Subfields: Artificial Intelligence, Cancer Research, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/ae0a728d10e4c61a66021bc02b01e7bdd13030b9

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Cancer Research

In Computer Vision and Pattern Recognition

Citations in the corpus

Reducing Domain Gap via Style-Agnostic Networks (2019, methodology): “When a model is learned with multiple domains, it has been reported that using separate BN modules for individual domains helps to align their feature distributions [17, 3, 4].”
Cross-Domain First Person Audio-Visual Action Recognition through Relative Norm Alignment (2021, background): “Other works exploit batch normalization layers to normalize source and target statistics [32, 33, 9].”
Learning to Optimize Domain Specific Normalization for Domain Generalization (2019, methodology): “A recent work using domain-specific batch normalization (DSBN) [5] has shown competitive performance in multi-source domain adaptation by aligning the representations in heterogeneous domains to a single common feature space.”
FedBN: Federated Learning on Non-IID Features via Local Batch Normalization (2021, methodology): “Here, an effective approach in practice is utilizing Batch Normalization (BN) (Ioffe & Szegedy, 2015): recent work has proposed BN as a tool to mitigate domain shifts in domain adaptation tasks with promising results achieved (Li et al., 2016; Liu et al., 2020; Chang et al., 2019).”
Class-Incremental Domain Adaptation (2020, background): “A line of work called Unsupervised Domain Adaptation (UDA) [2,3,5,21,25,31,22,51] has emerged that offers an elegant solution to the domain-shift problem.”
Universal Domain Adaptation through Self Supervision (2020, methodology): “4 Training with Domain Specific Batch Normalization To enhance alignment between source and target domain, we propose to utilize domain-specific batch normalization [7, 23, 34].”
Stochastic Classifiers for Unsupervised Domain Adaptation (2020, methodology): “Based on adversarial training, some other strategies, e.g., dropout [44] and domain-specific batch normalisation (DSBN) [3], have been proposed to impose on previous methods.”
CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation (2021, neutral): “We compare our method with state-of-the-art methods on UDA tasks, including MinEnt (Grandvalet et al., 2005), DANN (Ganin & Lempitsky, 2015), CDAN+E (Long et al., 2018), CDAN+BSP (Chen et al., 2019), CDAN+TN (Wang et al., 2019), rRGrad+CAT (Deng et al., 2019), MCD (Saito et al., 2018), SWD (Lee et a”
Deep Multimodal Fusion by Channel Exchanging (2020, methodology): “Although this idea is previously studied in [8, 47], we apply it here to serve specific purposes in CEN: by using private BNs, as already discussed above, we can determine the channel importance for each individual modality; by sharing convolutional filters, the corresponding channels among differen”
MS-Net: Multi-Site Network for Improving Prostate Segmentation With Heterogeneous MRI Data (2020, background): “[22] observed that independently nor-”
Source Data-Absent Unsupervised Domain Adaptation Through Hypothesis Transfer and Labeling Transfer (2020, methodology): “For vanilla unsupervisedDA in digit recognition, we compare SHOT with ADDA [5], ADR [56], CDAN [42], CyCADA [8], CAT [98], SWD [99] and STAR [100]; for object recognition, we compare ours with DANN [24], DAN [4], SAFN [82], BSP [101], MDD [102], TransNorm [55], DSBN [25], BNM [103] and GVB-GD [104].”
Batch Coherence-Driven Network for Part-Aware Person Re-Identification (2020, methodology): “Inspired by BN, several works have proposed adopting batch-level information for domain adaptation [47], [48].”