DSGC unifies graph and grid convolutions.
problem Lack of understanding between graph and grid convolutions.
method Depthwise separable graph convolution.
result DSGC outperforms existing methods on benchmark datasets.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
169,291 papers · 148 categories
Trend · papers per month
48 results for “Depthwise convolutions”
A new method speeds up spectral normalization for neural nets.
problem Efficiently controlling the spectral norm of convolutional layers.
method Depthwise separable convolutions with spectral normalization.
result Significant reduction in computational and memory costs.
WaveletNet improves edge device efficiency with logarithmic convolution.
problem Efficiency and performance on edge devices for CNNs.
method Introduces WaveletNet architecture with wavelet convolution and depthwise fast wavelet transform.
result WaveletNet achieves superior and comparable performance to state-of-the-art models on CIFAR-10 and ImageNet.
XceptionTime improves hand gesture recognition accuracy using novel deep learning.
problem Improving hand gesture recognition from sparse sEMG signals.
method Depthwise separable convolutions, adaptive pooling, non-linear normalization.
result Significantly improved accuracy (5.71% improvement) in hand gesture recognition.
A modified VDCNN model reduces size and latency for mobile platforms.
problem Memory and processing constraints on mobile platforms.
method Temporal Depthwise Separable Convolutions and Global Average Pooling.
result The squeezed model (SVDCNN) is 10x-20x smaller with minimal accuracy loss.
Paper proposes DeCEF layers to reduce CNN complexity.
problem Reduces complexity of CNNs without pre-trained models.
method Develops Depthwise Convolutional Eigen-Filter (DeCEF) layers.
result Achieves similar or higher accuracy with 2/3 parameters and 2/3 FLOPs.
Proposes a new interpretation of separable convolutions.
problem Lack of a thorough explanation for the efficacy of separable convolutions.
method Hybrid interpretation combining depthwise and pointwise convolutions.
result Proposes a new model for understanding separable convolutions.
Residual networks with depthwise hyperparameter scaling transfer optimal hyperparameters across width and depth.
problem The challenge of hyperparameter tuning in deep learning, especially for large models.
method Combining P parameterization with residual networks having a residual branch scale of .
result Optimal hyperparameters transfer across width and depth in residual networks trained with this parameterization.
New bounds for CNNs show better generalization than previous models.
problem Improving understanding of CNNs' generalization ability.
method Proposed tighter generalization bounds for CNNs by exploiting the sparse and permutation structure of weight matrices and spectral norms of convolution operations.
result Theoretical and experimental results show tighter bounds for CNNs than existing bounds.
EEGNet creates a compact CNN for EEG-based BCIs across various paradigms.
problem Designing a single CNN for EEG-based BCIs that works across different paradigms.
method Use of depthwise and separable convolutions to create an EEG-specific model.
result EEGNet generalizes across paradigms better than current state-of-the-art approaches.
TaLK Convolutions improve sequence modeling efficiency.
problem Efficiently modeling sequences with limited time complexity.
method Adaptive convolution operation that learns kernel size.
result Time complexity reduced to , making sequence encoding linear.
Random convolutional neural network improves image classification and retrieval.
problem Improving image classification and retrieval performance.
method Random depthwise signed convolutional neural network.
result Higher accuracy in image classification and retrieval compared to baseline models.
MASnet enhances speech on mobile devices with low latency.
problem Efficiently enhancing speech on mobile devices with low latency.
method MASnet processes linear-scale spectrograms, using ratio masks to enhance noisy frames, and operates in low-latency incremental inference mode.
result MASnet achieves efficient speech enhancement with low latency, reducing FMA/s operations.
New tensor network decompositions improve CNN performance.
problem Limited exploration of tensor network decompositions for CNNs.
method Characterized a new class of CNN modules and experimentally compared various decompositions.
result Some nonlinear decompositions outperform existing ones in terms of accuracy and efficiency.
The paper bridges spectral and spatial graph convolutions, improving model capacity and transferability.
problem Improving graph neural networks by bridging spectral and spatial design.
method Theoretical demonstration and general framework for spectral analysis, new spectral convolutions, and depthwise separable convolutions.
result General framework allows spectral analysis of ConvGNNs, showing their performance and limits, and proposing new spectral convolutions.
Researchers enhance EfficientNet models for practical efficiency on Graphcore IPU.
problem Improving practical efficiency of EfficientNet models on high-performance accelerators.
method Group convolutions, proxy-normalized activations, and reduced training resolution.
result Improves practical efficiency for both training and inference on Graphcore IPU.
A simple CNN architecture outperforms complex ones in P300 detection.
problem Efficiently detecting P300 component from EEG signals.
method Used a simple CNN architecture with a single depthwise separable 1D convolutional layer followed by a fully connected Sigmoid neuron.
result A single depthwise separable 1D convolutional layer with four filters achieved competitive performance.
QuickNet is a faster, more accurate deep learning model.
problem Improving deep learning model efficiency and accuracy.
method Modified Darknet model with depthwise separable convolutions and parametric rectified linear units.
result QuickNet achieves 95.7% accuracy on CIFAR-10 dataset, faster than other models.
Mobile app uses CNN to help visually impaired cross streets.
problem Helping visually impaired cross streets safely.
method LytNetV2 deep learning model for pedestrian traffic light detection.
result 96% classification accuracy and 6.15 degree angle error.
Real-time drowsiness detection on mobile phones reduces road trauma.
problem Driver drowsiness increases crash risk and road trauma.
method Depthwise separable 3D convolutions combined with early fusion of spatial and temporal information.
result Real-time drowsiness detection on mobile phones reduces road trauma.
BlurNet defends against adversarial attacks by filtering feature maps.
problem Adversarial attacks on deep neural networks, especially for image classification.
method BlurNet introduces a depthwise convolution layer with standard blur kernels after the first layer to filter high frequency noise.
result The defense reduces the success rate of adversarial attacks from 90% to 20% with total variation regularization.
A new method learns discrete representations for images and videos, improving upon previous models.
problem Learning discrete representations for images and videos to improve performance.
method Depthwise application of Vector Quantized Variational Autoencoders (VQVAE) to feature axis.
result 33% improvement in performance compared to previous discrete models.
DeepCAM learns convolutional dictionaries for image processing.
problem Processing high-dimensional signals like images efficiently.
method Introduces a Deep Convolutional Analysis Dictionary Model (DeepCAM) using convolutional dictionaries.
result DeepCAM achieves performance comparable to other methods on single image super-resolution.
Improved generative models using flexible convolutions.
problem Generating high-quality images efficiently.
method Generalized 1 x 1 convolutions to d x d convolutions, chaining autoregressive and periodic convolutions.
result Flexible d x d convolutions significantly improve generative flow models' performance.
Introduces Finslerian convolution metrics and their properties.
problem No specific problem stated; focuses on new metric concept.
method Definition and study of Finslerian convolution metrics.
result Characterization of Finslerian convolution metrics of Riemannian, Minkowskian, and Randers types.
TAGCN improves graph CNN performance without approximation.
problem Performance loss in spectral graph convolutional neural networks.
method Topology adaptive graph convolutional network (TAGCN) with adaptive filters.
result TAGCN outperforms existing spectral CNNs on various datasets.
New PTC convolution preserves properties of Euclidean convolutions on manifolds.
problem Lack of generalizable convolutions on curved domains with desirable properties.
method Parallel transport convolution (PTC) on Riemannian manifolds.
result PTC preserves compactly supported filters and directionality.
VC dimensions of group CNNs are infinite for certain kernels and groups.
problem Estimating the generalization capacity of group convolutional neural networks.
method Identifying precise VC dimension estimates for simple sets of group CNNs.
result Two-parameter families of convolutional neural networks have an infinite VC dimension for infinite groups and certain kernels.
We introduce a guide to help deep learning practitioners understand and manipulate convolutional neural network architectures. The guide clarifies the relationship between various properties (input shape, kernel shape, zero padding, strides and output shape) of convolutional, pooling and transposed convolutional layers…
ConvNets can be translated into CKNs that perform similarly.
problem The distinction between ConvNets and kernel-based methods.
method Translation of ConvNets into CKNs using a new gradient algorithm.
result CKNs perform as well as ConvNets, supporting the translation.
Spectral Convolution Networks speed up computation by applying convolution and activation in the frequency domain.
problem Performance increase in convolution networks comes with repeated transform computations.
method Implement convolution and activation in the frequency domain using Fourier or Laplace transformations.
result Reduced number of transforms and overall complexity by computing both convolution and activation in the frequency domain.
Enhances group convolutional networks with attention to learn meaningful relationships.
problem Lack of explicit means to learn meaningful relationships among symmetry patterns.
method Introduces attentive group equivariant convolutions, applying attention during convolution.
result Consistently outperforms conventional group convolutional networks on benchmark datasets.
We introduce Group equivariant Convolutional Neural Networks (G-CNNs), a natural generalization of convolutional neural networks that reduces sample complexity by exploiting symmetries. G-CNNs use G-convolutions, a new type of layer that enjoys a substantially higher degree of weight sharing than regular convolution la…
Proves DCNNs with expansive convolution are strongly universally consistent.
problem Theoretical consistency of deep convolutional neural networks (DCNNs).
method Empirical risk minimization on DCNNs with expansive convolution (with zero-padding).
result DCNNs with expansive convolution are strongly universally consistent.
New framework for manifold convolutions using toric embeddings.
problem Computational intractability of manifold convolutions.
method Isometric embeddings into tori for global manifold convolutions.
result Global definition of manifold convolutions on finite approximations.
Paper improves graph convolutional networks by adjusting filter size.
problem Improving predictive performance of graph convolutional networks.
method Introducing a hyper-parameter to influence filter size in graph convolutions.
result Improves predictive performance of Deep Graph Convolutional Networks.
Functor connects Lie groupoid algebras to bornological structures.
problem Establishing a functorial relationship between Lie groupoid convolution algebras and bornological structures.
method Developed a monoidal functor from differentiable stacks to Morita 2-category of complete bornological algebras.
result Convolution algebras are self-induced and convolution modules are smooth.
IEA improves CNN models by averaging multiple convolutional layers.
problem Improving CNN model accuracy through ensemble learning.
method Replacing single convolutional layers with Inner Average Ensembles (IEA) of multiple convolutional layers.
result CNN models using IEA outperform those with regular convolutional layers.
HexaConvcs.LG
HexaConv improves CNN performance by using hexagonal filters and group convolutions.
problem Improving CNN performance by exploiting more symmetries.
method Implementing planar and group convolutions over hexagonal lattices.
result HexaConv outperforms conventional CNNs on aerial scene classification.
New method enforces orthogonality in convolutional layers for improved robustness.
problem Improving adversarial robustness in deep learning models.
method Applying the Cayley transform to skew-symmetric convolutions in the Fourier domain.
result The proposed method preserves orthogonality and enhances adversarial robustness compared to existing techniques.
New method improves grouped convolutions on edge devices.
problem Efficiently implementing grouped convolutions on edge devices.
method Grouped Spatial Pack Convolutions (GSPC) in TVM.
result GSPC outperforms existing implementations by 3.4x, 8x, and 4x on average.
GCNs improve regression tasks by aggregating neighbor signals.
problem GCNs' statistical properties in regression tasks are poorly understood.
method Examined two GCN convolutions and their impact on learning error.
result GCNs have a bias-variance trade-off that depends on neighborhood size and topology.
Convolution and pooling improve kernel methods in image classification.
problem Understanding the interplay between approximation and generalization in convolutional architectures.
method Characterized RKHS of kernels with convolution, pooling, and downsampling, computed generalization error.
result Convolution and pooling operations trade off approximation with generalization power.
Convolutional networks outperform fully-connected ones in certain tasks.
problem Understanding the computational advantage of convolutional networks over fully-connected networks.
method Demonstrated a computational advantage through a specific problem class.
result Convolutional networks can solve certain problems that fully-connected networks cannot, even with gradient descent.
Proposes a method to constrain singular values of convolutional kernels in neural networks.
problem Avoiding exploding/vanishing gradient problems and improving generalizability in neural networks.
method Introduces a penalty function to constrain singular values of convolutional kernels around 1, and derives an algorithm for optimization.
result Demonstrates the effectiveness of the method through numerical examples.
Proposes a fixed smooth convolutional layer to reduce checkerboard artifacts in CNNs.
problem Checkerboard artifacts in CNNs during upsampling and strided convolution.
method Fixed convolutional layer with adjustable smoothness, applied to four CNNs and GANs.
result Significantly improves classification performance and image generation quality.
Adaptive convolution improves GANs performance on image generation.
problem GANs struggle with generating images of objects with diverse appearances.
method Proposes adaptive convolution to learn upsampling based on local context.
result Adaptive convolution models improve GANs performance on CIFAR-10 and STL-10 datasets.
On the Universal Statistical Consistency of Expansive Hyperbolic Deep Convolutional Neural Networksstat.ML
This work proposes hyperbolic deep convolutional neural networks for better pattern recognition.
problem The limitations of Euclidean deep convolutional neural networks in capturing intricate patterns.
method Developed Hyperbolic DCNN based on Poincaré Disc, analyzing expansive convolution in non-Euclidean space.
result Hyperbolic convolutional architecture outperforms Euclidean ones in pattern recognition tasks.