paper-with-me

Papers

Instance-Level Meta Normalization

2019-04-06 · CVPR 2019 6 · Songhao Jia, Ding-Jie Chen, Hwann-Tzong Chen

This paper presents a normalization mechanism called Instance-Level Meta Normalization (ILM~Norm) to address a learning-to-normalize problem. ILM~Norm learns to predict the normalization parameters via both the feature feed-forward and the gradient back-propagation paths. ILM~Norm provides a meta normalization mechanism and has several good properties. It can be easily plugged into existing instance-level normalization schemes such as Instance Normalization, Layer Normalization, or Group Normalization. ILM~Norm normalizes each instance individually and therefore maintains high performance even when small mini-batch is used. The experimental results show that ILM~Norm well adapts to different network architectures and tasks, and it consistently improves the performance of the original models. The code is available at url{https://github.com/Gasoonjia/ILM-Norm.

📄 PDF Abstract BibTeX arXiv:1904.03516

Code (1)

Gasoonjia/ILM-Norm 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Instance Normalization Instance Normalization (also known as contrast normalization) is a normalization layer where: $$ y_{tijk} = \frac{x_{tijk} - \mu_{ti}}{\sqrt{\sigma_{ti}^2 +…
Group Normalization Group Normalization is a normalization layer that divides channels into groups and normalizes the features within each group. GN does not exploit the batch dimension, and its…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Instance-Level Meta Normalization Instance-Level Meta Normalization is a normalization method that addresses a learning-to-normalize problem. ILM-Norm learns to predict the normalization parameters via both…

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

U-Net Training with Instance-Layer Normalization

2019-08-21 · Xiao-Yun Zhou, Peichao Li, Zhao-Yang Wang, Guang-Zhong Yang

Normalization layers are essential in a Deep Convolutional Neural Network (DCNN). Various normalization methods have been proposed. The statistics used to normalize the feature maps can be computed at batch, channel, or …

Image SegmentationSemantic Segmentation

Z-Score Normalization, Hubness, and Few-Shot Learning

2021-01-01 · ICCV 2021 10 · Nanyi Fei, Yizhao Gao, Zhiwu Lu, Tao Xiang

The goal of few-shot learning (FSL) is to recognize a set of novel classes with only few labeled samples by exploiting a large set of abundant base class samples. Adopting a meta-learning framework, most recent FSL m…

Few-Shot LearningMeta-Learning

MMO: Meta Multi-Objectivization for Software Configuration Tuning

2021-12-14 · Pengzhou Chen, Tao Chen, Miqing Li

Software configuration tuning is essential for optimizing a given performance objective (e.g., minimizing latency). Yet, due to the software's intrinsically complex configuration landscape and expensive measurement, ther…

Metadata Normalization

2021-04-19 · CVPR 2021 1 · Mandy Lu, Qingyu Zhao, Jiequan Zhang, Kilian M. Pohl 외

Batch Normalization (BN) and its variants have delivered tremendous success in combating the covariate shift induced by the training step of deep learning methods. While these techniques normalize feature distributions b…