MBS reduces CNN model size with minimal accuracy loss.
problem Reducing CNN model size while maintaining accuracy.
method Adaptive macroblock scaling based on effective flops.
result Significant model size reduction across various CNN architectures.
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.
169,051 papers · 148 categories
Trend · papers per month
48 results for “CNN model reduction”
BRIEF reduces CNN models by 32.3% on ImageNet, removing redundant channels.
problem Redundant neural channels in CNN models.
method Backward reduction algorithm based on information flow analysis.
result Significant model reduction (32.3%) on ResNet-34 in ImageNet scale.
Reduced CNN complexity for exoplanet detection without significant loss in accuracy.
problem Reducing the number of parameters in CNNs for time-series data.
method Two methods for complexity reduction in AstroNet: tactical reduction of layers and modification of input data.
result Non-substantial loss in accuracy with up to 85% reduction in training time.
Paper proposes scalable multi-label classification for edge devices using CNN.
problem Challenges in deploying multi-label CNN models on edge devices due to high computation and memory requirements.
method Extends existing multi-label classification methods with a single CNN model and multiple loss and accuracy layers.
result Achieves comparable accuracy with 1.8x less MACC operations, 0.97x reduction in latency and 0.5x, 0.84x, 0.97x reduction in size for generated CNN models.
PixelHop uses SSL for image classification, outperforming CNN.
problem Image classification accuracy improvement.
method PixelHop combines SSL with supervised and unsupervised dimension reduction.
result PixelHop outperforms CNN on MNIST, Fashion MNIST, and CIFAR-10 datasets.
Study on geodesic distances on SE(3)/SO(2) in machine learning.
problem Investigating the efficiency of computationally efficient sections in selecting geodesic distances.
method Analyzing geodesic distances on reductive homogeneous spaces, proving the efficiency of minimal distance sections.
result Minimal distance sections are not always geodesic minimizers, but minimal horizontal geodesics are.
Morph accelerates 3D CNNs for video recognition, reducing energy consumption and improving performance.
problem Efficiently accelerating 3D CNNs for video recognition is challenging due to their large memory footprint and higher dimensionality.
method Designing a flexible accelerator called Morph that adapts to different spatial and temporal tiling strategies, and codesigning a software infrastructure to control the hardware.
result Morph achieves up to 3.4x reduction in energy consumption and up to 5.1x improvement in performance/watt compared to a baseline 3D CNN accelerator.
Gradient Reduction Convolutional Neural Network Policy for Financial Deep Reinforcement Learningq-fin.CP
Enhanced CNN for financial data improves predictive accuracy and stability.
problem Complexity and variability in financial data.
method Normalization and Gradient Reduction Architecture.
result Improvement in model accuracy and stability.
First-order scattering reduces CNN input size while maintaining classification accuracy.
problem Reducing the input size of CNNs for faster inference and lower memory usage.
method First-order scattering transform applied to CNN inputs.
result Cascaded CNN with scattering transform achieves similar ImageNet classification performance.
CNNs improve InSAR image denoising and coherence estimation.
problem Noise in InSAR imagery corrupts ground movement estimates.
method Autoencoder CNN architectures for denoising and preprocessing.
result Proposed method outperforms four established methods.
GrateTile optimizes CNN feature map storage for efficient data access.
problem Efficient storage and access of sparse CNN feature maps.
method Divides feature maps into uneven-sized subtensors, compresses and stores them in a compressed yet accessible format.
result Average 55% DRAM bandwidth reduction with minimal indexing overhead.
Convolutional Neural Networks (CNNs) require a large amount of annotated data to learn from, which is often difficult to obtain in the medical domain. In this paper we show that the sample complexity of CNNs can be significantly improved by using 3D roto-translation group convolutions (G-Convs) instead of the more conv…
A new low-dimensional parameterization based on principal component analysis (PCA) and convolutional neural networks (CNN) is developed to represent complex geological models. The CNN-PCA method is inspired by recent developments in computer vision using deep learning. CNN-PCA can be viewed as a generalization of an ex…
LeanResNet reduces CNN complexity without sacrificing accuracy.
problem High computational cost in CNNs, especially in ResNets.
method Introduces lean convolution operators that reduce parameters and complexity.
result LeanResNet achieves comparable results to other reduced architectures with fewer parameters.
Synaptic pruning reduces CNNs by 96% on CIFAR-10.
problem Memory and computation constraints in CNNs for mobile devices.
method Synaptic Pruning: data-driven method to prune connections based on Synaptic Strength.
result Significant size reduction and computation saving with up to 96% pruning on CIFAR-10.
RCCNet simplifies CNN for efficient colon cancer nuclei classification.
problem Efficient and precise classification of histological cell nuclei for medical analysis.
method Proposes RCCNet, a simplified CNN architecture with 1.5M parameters.
result Achieved 80.61% accuracy and 0.7887 F1 score on CRCHistoPhenotypes dataset.
BIL allows binary input data in CNNs, improving performance on multimodal datasets.
problem Efficient execution of CNNs on edge devices with reduced bit width.
method BIL concept that learns bit-specific binary weights for binary input data.
result BIL outperforms full precision weights by 1.92% on multimodal datasets.
CNN improves OSA diagnosis accuracy from PSG data.
problem Manual PSG analysis by specialists is tedious, time-consuming, and prone to errors.
method 1D CNN architecture with convolutional and FCN layers for OSA severity classification.
result Proposed CNN model achieves excellent classification results without manual preprocessing.
Post-hoc explanations improve CNNs by replacing final linear layer with k-means classifier.
problem CNNs lack accurate data representation in their built-in prototypes.
method Introduces k-means-based post-hoc explanations for CNNs, leveraging spatial consistency of convolutional receptive fields.
result Using shallower, less compressed feature activations improves semantic fidelity at the cost of slight predictive performance.
An Unsupervised Generative Neural Approach for InSAR Phase Filtering and Coherence Estimationeess.IV
GenInSAR uses CNNs to filter InSAR phase and estimate coherence without supervision.
problem Improving accuracy in InSAR phase filtering and coherence estimation.
method Unsupervised CNN-based generative model for joint phase filtering and coherence estimation.
result GenInSAR outperforms five related methods in residue reduction and coherence estimation.
New approximative kernels improve PDE-G-CNNs for geometric deep learning.
problem Inaccurate approximations of exact kernels in PDE-G-CNNs.
method Developed new approximative kernels that work regardless of spatial anisotropy.
result New kernels provide better error estimates and maintain reflectional symmetries.
Collage inference uses redundancy to reduce cloud image classification latency variance.
problem Reducing latency variance in cloud image classification.
method Integrates collage-cnn for low-cost redundancy in multi-image classification.
result Significant reduction in 99th percentile tail latency and inference latency variation.
CNN improves medium-range temperature forecasts with limited resources.
problem Limited computational resources for high-resolution temperature forecasts.
method CNN post-processing with ensemble NWP models for bias correction and spatial downscaling.
result High-resolution (5-km) surface temperature forecasts with lead times up to 5.5 days.
Ensemble of diverse CNNs detects and mitigates adversarial attacks.
problem Detecting and defending against adversarial attacks.
method An ensemble of specialized CNNs with a voting mechanism.
result Significant reduction in adversarial attack risk rate.
In this paper, we propose a deep multimodal fusion network to fuse multiple modalities (face, iris, and fingerprint) for person identification. The proposed deep multimodal fusion algorithm consists of multiple streams of modality-specific Convolutional Neural Networks (CNNs), which are jointly optimized at multiple fe…
Efficient text classification model reduces size and speeds up inference.
problem Label-scarce conditions in text classification.
method Convolutional student architecture trained by distillation from a transformer teacher.
result 300x inference speedup and 39x reduction in parameter count.
Large receptive field CNNs improve distant speech recognition.
problem Degrading performance of ASR systems in noisy environments.
method Investigated large receptive field CNN variants including recursive, dilated, and hourglass networks.
result Stacked hourglass networks show significant improvements in distant speech recognition.
New multigrid approach reduces CNN parameters by focusing on structured convolutions.
problem Redundancy in standard CNNs leads to high parameter count.
method Replace standard convolutions with structured multilevel convolutions.
result Linearly proportional number of parameters to network width, no loss in accuracy.
A deep learning algorithm designs low-cost SPP films.
problem Designing SPP films with high accuracy and low cost.
method Guided deep learning algorithm with low-cost sample replacement.
result Deep CNN learns to replace precious metals with ordinary metals, reducing cost.
New metric assesses image dataset complexity.
problem Assessing the complexity of image classification datasets.
method Cumulative Spectral Gradient (CSG) derived from spectral clustering.
result CSG correlates with CNN test accuracy and dataset separability.
Reduces CNN parameters by 2x with minimal loss in accuracy.
problem Parameter efficiency in distributed machine learning and edge devices.
method Introduces a Convolutional Slice Generator (CSG) to reduce CNN parameters.
result Reduces CNN parameters by approximately 2x with minimal accuracy loss.
New method uses eigenspectrum to optimize object detector architectures.
problem Understanding the effects of ImageNet pre-training on object detectors.
method Analysis of eigenspectrum dynamics of feature maps in object detectors.
result Object detectors trained from scratch and ImageNet pre-trained models behave differently.
A new spectral pooling method reduces loss in CNNs for better performance.
problem Lossy downsampling in CNNs reduces discriminability.
method Hartley Spectral Pooling using Hartley Transform.
result Hartley Spectral Pooling preserves more structure features than max/average pooling.
Edge-Efficient Deep Learning Models for Automatic Modulation Classification: A Performance Analysiseess.SP
Optimized CNNs for AMC on edge devices reduce complexity without sacrificing accuracy.
problem Developing efficient DL models for AMC on resource-constrained edge devices.
method Pruning, quantization, and knowledge distillation techniques applied to CNNs.
result Optimized models maintain or improve AMC accuracy with reduced complexity.
Generalized Bilinear Deep Convolutional Neural Networks for Multimodal Biometric Identificationcs.LG
In this paper, we propose to employ a bank of modality-dedicated Convolutional Neural Networks (CNNs), fuse, train, and optimize them together for person classification tasks. A modality-dedicated CNN is used for each modality to extract modality-specific features. We demonstrate that, rather than spatial fusion at the…
The current trend of pushing CNNs deeper with convolutions has created a pressing demand to achieve higher compression gains on CNNs where convolutions dominate the computation and parameter amount (e.g., GoogLeNet, ResNet and Wide ResNet). Further, the high energy consumption of convolutions limits its deployment on m…
This paper introduces channel gating, a dynamic, fine-grained, and hardware-efficient pruning scheme to reduce the computation cost for convolutional neural networks (CNNs). Channel gating identifies regions in the features that contribute less to the classification result, and skips the computation on a subset of the …
Deep learning predicts heart failure readmission from clinical notes.
problem Predicting and preventing heart failure readmission.
method Convolutional Neural Networks (CNN) trained on clinical notes.
result Deep learning models outperform traditional machine learning methods in readmission prediction.
Discrete Fourier transforms provide a significant speedup in the computation of convolutions in deep learning. In this work, we demonstrate that, beyond its advantages for efficient computation, the spectral domain also provides a powerful representation in which to model and train convolutional neural networks (CNNs).…
Convolutional neural networks (CNNs) achieve state-of-the-art performance in a wide variety of tasks in computer vision. However, interpreting CNNs still remains a challenge. This is mainly due to the large number of parameters in these networks. Here, we investigate the role of compression and particularly pruning fil…
Filters in a Convolutional Neural Network (CNN) contain model parameters learned from enormous amounts of data. In this paper, we suggest to decompose convolutional filters in CNN as a truncated expansion with pre-fixed bases, namely the Decomposed Convolutional Filters network (DCFNet), where the expansion coefficient…
Improved ASR for English-isiZulu code-switched speech with semi-supervised training.
problem Improving ASR for code-switched speech between English and isiZulu.
method Semi-supervised training using automatic transcription of multilingual speech data.
result Semi-supervised training achieved significant WER reduction in ASR performance.
GradiVeQ reduces CNN training time by 50% with 5X faster gradient aggregation.
problem Significant communication costs in gradient aggregation for distributed CNN training.
method GradiVeQ uses PCA to vector quantize gradients for direct RAR aggregation.
result GradiVeQ reduces wall-clock gradient aggregation time by more than 5X.
Approximate multipliers boost CNN training speed, power, and area at slight accuracy cost.
problem Improving CNN training performance in terms of speed, power, and area.
method Simulation of approximate multipliers' impact on CNN training, hybrid training method combining approximate and exact multipliers.
result Using approximate multipliers for most of training enhances speed, power, and area with minimal accuracy loss.
This work studies the entity-wise topical behavior from massive network logs. Both the temporal and the spatial relationships of the behavior are explored with the learning architectures combing the recurrent neural network (RNN) and the convolutional neural network (CNN). To make the behavioral data appropriate for th…
This work reduces computation cost for on-device CNN training.
problem High computation cost during on-device CNN training.
method Self-supervised instance filtering and error map pruning.
result Substantial computation saving without significant accuracy loss.
In a previous work we have detailed the requirements to obtain a maximal performance benefit by implementing fully connected deep neural networks (DNN) in form of arrays of resistive devices for deep learning. This concept of Resistive Processing Unit (RPU) devices we extend here towards convolutional neural networks (…
New method reduces version space for CNNs, improving active learning performance.
problem Sampling bias in active learning hinders optimal hypothesis finding in neural networks.
method Version space reduction through prior mass reduction and diameter reduction, proposing a new Gibbs-vote disagreement method.
result Diameter-based querying method reduces version space more effectively than prior mass reduction and other methods.