paper-with-me

Papers

Kalman Normalization: Normalizing Internal Representations Across Network Layers

2018-12-01 · NeurIPS 2018 12 · Guangrun Wang, Jiefeng Peng, Ping Luo, Xinjiang Wang, Liang Lin

As an indispensable component, Batch Normalization (BN) has successfully improved the training of deep neural networks (DNNs) with mini-batches, by normalizing the distribution of the internal representation for each hidden layer. However, the effectiveness of BN would diminish with the scenario of micro-batch (e.g. less than 4 samples in a mini-batch), since the estimated statistics in a mini-batch are not reliable with insufficient samples. This limits BN's room in training larger models on segmentation, detection, and video-related problems, which require small batches constrained by memory consumption. In this paper, we present a novel normalization method, called Kalman Normalization (KN), for improving and accelerating the training of DNNs, particularly under the context of micro-batches. Specifically, unlike the existing solutions treating each hidden layer as an isolated system, KN treats all the layers in a network as a whole system, and estimates the statistics of a certain layer by considering the distributions of all its preceding layers, mimicking the merits of Kalman Filtering. On ResNet50 trained in ImageNet, KN has 3.4% lower error than its BN counterpart when using a batch size of 4; Even when using typical batch sizes, KN still maintains an advantage over BN while other BN variants suffer a performance degradation. Moreover, KN can be naturally generalized to many existing normalization variants to obtain gains, e.g. equipping Group Normalization with Group Kalman Normalization (GKN). KN can outperform BN and its variants for large scale object detection and segmentation task in COCO 2017.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

object-detectionObject Detection

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Average Pooling 설명 없음
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Residual Connection 설명 없음
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…

Similar Papers 제목 키워드 기반

Batch Kalman Normalization: Towards Training Deep Neural Networks with Micro-Batches

2018-02-09 · Guangrun Wang, Jiefeng Peng, Ping Luo, Xinjiang Wang 외

As an indispensable component, Batch Normalization (BN) has successfully improved the training of deep neural networks (DNNs) with mini-batches, by normalizing the distribution of the internal representation for each hid…

image-classificationImage Classification

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

2015-02-11 · Sergey Ioffe, Christian Szegedy

Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change. This slows down the training by requiring lo…

General Classificationimage-classificationImage Classification

K-Score: Kalman Filter as a Principled Alternative to Reward Normalization in Reinforcement Learning

2026-04-24 · Zixuan Xia, Quanxi Li arxiv

We propose a simple yet effective alternative to reward normalization in policy gradient reinforcement learning by integrating a 1D Kalman filter for online reward estimation. Instead of relying on fixed heuristics, our …

Reinforcement Learning

Riemannian approach to batch normalization

2017-09-27 · NeurIPS 2017 12 · Minhyung Cho, Jaehyung Lee

Batch Normalization (BN) has proven to be an effective algorithm for deep neural network training by normalizing the input to each neuron and reducing the internal covariate shift. The space of weight vectors in the BN l…

Adversarial normalization for multi domain image segmentation

2019-12-02 · Pierre-Luc Delisle, Benoit Anctil-Robitaille, Christian Desrosiers, Herve Lombaert

Image normalization is a critical step in medical imaging. This step is often done on a per-dataset basis, preventing current segmentation algorithms from the full potential of exploiting jointly normalized information a…

Image SegmentationSegmentationSemantic Segmentation