paper-with-me

홈 › Papers

NAM: Normalization-based Attention Module

2021-11-24 · NeurIPS Workshop ImageNet_PPF 2021 12 · Yichao Liu, Zongru Shao, Yueyang Teng, Nico Hoffmann

Recognizing less salient features is the key for model compression. However, it has not been investigated in the revolutionary attention mechanisms. In this work, we propose a novel normalization-based attention module (NAM), which suppresses less salient weights. It applies a weight sparsity penalty to the attention modules, thus, making them more computational efficient while retaining similar performance. A comparison with three other attention mechanisms on both Resnet and Mobilenet indicates that our method results in higher accuracy. Code for this paper can be publicly accessed at https://github.com/Christian-lyc/NAM.

📄 PDF Abstract BibTeX arXiv:2111.12419

Code (1)

christian-lyc/nam 공식 구현 pytorch

Tasks

Model Compression

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…
Batch Normalization 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…
Average Pooling 설명 없음
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…
Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…

Similar Papers 제목 키워드 기반

SAFIN: Arbitrary Style Transfer With Self-Attentive Factorized Instance Normalization

2021-05-13 · Aaditya Singh, Shreeshail Hingane, Xinyu Gong, Zhangyang Wang

Artistic style transfer aims to transfer the style characteristics of one image onto another image while retaining its content. Existing approaches commonly leverage various normalization techniques, although these face …

Style Transfer

U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation

2019-07-25 · ICLR 2020 1 · Junho Kim, Minjae Kim, Hyeonwoo Kang, Kwanghee Lee

We propose a novel method for unsupervised image-to-image translation, which incorporates a new attention module and a new learnable normalization function in an end-to-end manner. The attention module guides our model t…

Fundus to Angiography GenerationImage-to-Image TranslationTranslationUnsupervised Image-To-Image Translation

Attention Normalization Impacts Cardinality Generalization in Slot Attention

2024-07-04 · Markus Krimmel, Jan Achterhold, Joerg Stueckler

Object-centric scene decompositions are important representations for downstream tasks in fields such as computer vision and robotics. The recently proposed Slot Attention module, already leveraged by several derivative …

Image SegmentationObjectObject TrackingSemantic Segmentation+1

Normalized and Geometry-Aware Self-Attention Network for Image Captioning

2020-03-19 · CVPR 2020 6 · Longteng Guo, Jing Liu, Xinxin Zhu, Peng Yao 외

Self-attention (SA) network has shown profound value in image captioning. In this paper, we improve SA from two aspects to promote the performance of image captioning. First, we propose Normalized Self-Attention (NSA), a…

Image CaptioningMachine TranslationQuestion AnsweringTranslation+3

iRNN: Integer-only Recurrent Neural Network

2021-09-20 · Eyyüb Sari, Vanessa Courville, Vahid Partovi Nia

Recurrent neural networks (RNN) are used in many real-world text and speech applications. They include complex modules such as recurrence, exponential-based activation, gate interaction, unfoldable normalization, bi-dire…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Quantizationspeech-recognition+1