paper-with-me

홈 › Papers

Batch-Instance Normalization for Adaptively Style-Invariant Neural Networks

2018-05-21 · NeurIPS 2018 12 · Hyeonseob Nam, Hyo-Eun Kim

Real-world image recognition is often challenged by the variability of visual styles including object textures, lighting conditions, filter effects, etc. Although these variations have been deemed to be implicitly handled by more training data and deeper networks, recent advances in image style transfer suggest that it is also possible to explicitly manipulate the style information. Extending this idea to general visual recognition problems, we present Batch-Instance Normalization (BIN) to explicitly normalize unnecessary styles from images. Considering certain style features play an essential role in discriminative tasks, BIN learns to selectively normalize only disturbing styles while preserving useful styles. The proposed normalization module is easily incorporated into existing network architectures such as Residual Networks, and surprisingly improves the recognition performance in various scenarios. Furthermore, experiments verify that BIN effectively adapts to completely different tasks like object classification and style transfer, by controlling the trade-off between preserving and removing style variations. BIN can be implemented with only a few lines of code using popular deep learning frameworks.

📄 PDF Abstract BibTeX arXiv:1805.07925

Code (3)

hyeonseob-nam/Batch-Instance-Normalization 공식 구현 pytorch
hyeonseobnam/batch-instance-normalization pytorch
taki0112/Batch_Instance_Normalization-Tensorflow tf

Tasks

Style Transfer

Similar Papers 제목 키워드 기반

Meta Batch-Instance Normalization for Generalizable Person Re-Identification

2020-11-30 · CVPR 2021 1 · Seokeon Choi, Taekyung Kim, Minki Jeong, Hyoungseob Park 외

Although supervised person re-identification (Re-ID) methods have shown impressive performance, they suffer from a poor generalization capability on unseen domains. Therefore, generalizable Re-ID has recently attracted g…

Data AugmentationDomain GeneralizationGeneralizable Person Re-identificationMeta-Learning+2

MLA-BIN: Model-level Attention and Batch-instance Style Normalization for Domain Generalization of Federated Learning on Medical Image Segmentation

2023-06-29 · Fubao Zhu, Yanhui Tian, Chuang Han, Yanting Li 외

The privacy protection mechanism of federated learning (FL) offers an effective solution for cross-center medical collaboration and data sharing. In multi-site medical image segmentation, each medical site serves as a cl…

Domain GeneralizationFederated LearningImage SegmentationMedical Image Segmentation+1

Style-Label-Free: Cross-Speaker Style Transfer by Quantized VAE and Speaker-wise Normalization in Speech Synthesis

2022-12-13 · Chunyu Qiang, Peng Yang, Hao Che, Xiaorui Wang 외

Cross-speaker style transfer in speech synthesis aims at transferring a style from source speaker to synthesised speech of a target speaker's timbre. Most previous approaches rely on data with style labels, but manually-…

Data AugmentationSpeech SynthesisStyle Transfer

Proxy-Normalizing Activations to Match Batch Normalization while Removing Batch Dependence

2021-06-07 · NeurIPS 2021 12 · Antoine Labatie, Dominic Masters, Zach Eaton-Rosen, Carlo Luschi

We investigate the reasons for the performance degradation incurred with batch-independent normalization. We find that the prototypical techniques of layer normalization and instance normalization both induce the appeara…

Invariant Batch Normalization for Multi-source Domain Generalization

2021-01-01 · Qing Lian, LIN Yong, Tong Zhang

We consider the domain generalization problem, where the test domain differs from the training domain. For deep neural networks, we show that the batch normalization layer is a highly unstable component under such domain…

Domain Generalization