A real-time algorithm for signal analysis with the help of the wavelet transform

By M. Holschneider, R. Kronland-Martinet, J. Morlet, P. Tchamitchian. 1989

How researchers see this paper

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

In Speech & Audio

Citations in the corpus

Fully convolutional networks for semantic segmentation (2014, methodology): “(This trick is also used in the algorithme à trous [46], [47] for wavelet transforms and related to the Noble identities [48] from signal processing.”
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation (2020, methodology): “Some employ atrous convolu-tions [32,72,62,12], larger kernel [65], or image pyramids [92,80], either designed by hand or searched by algorithms [97,11,55].”
SSD: Single Shot MultiBox Detector (2015, methodology): “Similar to DeepLab-LargeFOV [17], we convert fc6 and fc7 to convolutional layers, subsample parameters from fc6 and fc7, change pool5 from 2 × 2 − s2 to 3 × 3 − s1, and use the à trous algorithm [18] to fill the ”holes”.”
WaveNet: A Generative Model for Raw Audio (2016, methodology): “Dilated convolutions have previously been used in various contexts, e.g. signal processing (Holschneider et al., 1989; Dutilleux, 1989), and image segmentation (Chen et al., 2015; Yu & Koltun, 2016).”
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs (2016, methodology): “We advocate instead the use of atrous convolution, originally developed for the efficient computation of the undecimated wavelet transform in the “algorithme a trous” scheme of [15] and used before in the DCNN context by [3], [6], [16].”
CrossTransformers: spatially-aware few-shot transfer (2020, methodology): “For experiments with CrossTransformers, we also increased the resolution of the convolutional feature map by setting the stride of final block of the ResNet to 1, and using dilated convolutions to preserve the feature computation [32, 39].”
Deformable Convolutional Networks (2017, background): “This partially explains why atrous convolution [23] is widely used in vision tasks (see below).”
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation (2018, methodology): “In this section, we briefly introduce atrous convolution [30, 21, 64, 56, 8] and depthwise separable convolution [67, 71, 74, 12, 31].”
Rethinking Atrous Convolution for Semantic Image Segmentation (2017, methodology): “Instead, we advocate the use of ‘atrous convolution’, originally developed for the efficient computation of the undecimated wavelet transform in the “algorithme à trous” scheme of [30] and used before in the DCNN context by [21, 64, 56].”
Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation (2019, neutral): “Therefore, PSPNet [87] performs spatial pyramid pooling [21, 41, 24] at several grid scales (including image-level pooling [50]), while DeepLab [8, 9] applies several parallel atrous convolution [28, 20, 67, 57, 7] with different rates.”
Searching for Efficient Multi-Scale Architectures for Dense Image Prediction (2018, background): “Several works have focused on sampling rates in atrous convolution to encode multi-scale context [37, 29, 77, 62, 10, 94, 11].”
Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers (2020, background): “This includes large kernel sizes [39], atrous convolutions [7, 21], and image/feature pyramids [58].”
DSSD : Deconvolutional Single Shot Detector (2017, methodology): “Then following the `a trous al-gorithm [15], for all convolution layers in conv5 stage with kernel size larger than 1, we increase their dilation from 1 to 2 to ﬁx the ”holes” caused by the reduced stride.”
Scale-Aware Trident Networks for Object Detection (2019, background): “Dilated convolution [41] (aka Atrous convolution [20]) enlarges the convolution kernel with original weights by performing convolution at sparsely sampled locations, thus increasing the receptive field size without additional cost.”
Understanding Convolution for Semantic Segmentation (2017, methodology): “Dilated Convolution: Dilated Convolution (or Atrous convolution) was originally developed in algorithme à trous for wavelet decomposition [14].”