In this paper, we address the issue of how to enhance the generalization performance of convolutional neural networks (CNN) in the early learning stage for image classification. This is motivated by real-time applications that require the generalization performance of CNN to be satisfactory within limited training time…
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 Accuracy”
UGConvs improve CNN accuracy with unitary transforms.
problem Improving CNN accuracy with richer representations.
method UGConvs combine group convolutions with unitary transforms.
result HadaNets achieve similar accuracy to circulant networks with lower complexity.
Simplified Butterfly-Net2 improves CNN efficiency in solving PDEs and signal processing tasks.
problem Improving CNN efficiency in solving PDEs and signal processing tasks.
method Introducing BNet2, a simplified Butterfly-Net, and Fourier transform initialization.
result BNet2 achieves similar accuracy as CNN but with fewer parameters and improves accuracy over randomly initialized CNN.
Paper proposes a new technique to compress CNNs while maintaining accuracy.
problem CNNs struggle with traditional low-rank approximation methods, leading to degraded accuracy.
method Introduces a training technique that finds a flat minimum in low-rank approximation without a decomposed structure.
result CNN models can be compressed with higher accuracy and lower computation than conventional methods.
Focused quantization reduces CNN models by 18x while maintaining accuracy.
problem Memory and compute resource constraints in deploying CNNs on constrained devices.
method Focused quantization, exploiting weight distributions after pruning, dynamically discovers optimal numerical representations.
result Achieved a 18.08x compression ratio with only 0.24% loss in accuracy in ResNet-50.
Advanced video classification systems decode video frames to derive the necessary texture and motion representations for ingestion and analysis by spatio-temporal deep convolutional neural networks (CNNs). However, when considering visual Internet-of-Things applications, surveillance systems and semantic crawlers of la…
New graph CNN layers improve accuracy on graph datasets.
problem Graph data relations are better represented as graphs, not grids.
method Proposed new graph CNN layers for vertex and edge features.
result Improved classification accuracy on graph datasets.
Short-segment heart sound classification using an ensemble of deep convolutional neural networkscs.SD
Paper uses CNNs to classify heart sounds from short segments.
problem Classifying heart sounds from short segments of individual beats.
method Developed a 1D-CNN and 2D-CNN ensemble for feature learning and score-level fusion.
result ECNN ensemble achieved 89.22% accuracy and 89.94% sensitivity on the PhysioNet CinC 2016 database.
Ensemble CNNs improve mode classification in smartphone travel surveys.
problem Classifying transportation modes from smartphone travel survey data.
method Developed an ensemble of CNN models with different architectures and hyper-parameters, combined using average voting, majority voting, optimal weights, and a Random Forest meta-learner.
result The ensemble method with Random Forest as meta-learner achieved 91.8% accuracy, surpassing other methods.
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.
AT-CNNs show improved shape recognition over texture recognition.
problem Understanding adversarial training's impact on CNNs' feature learning.
method Systematic qualitative and quantitative approaches to interpret AT-CNNs.
result Adversarial training reduces texture bias and improves shape recognition.
RIFLE improves deep transfer learning by reinitializing fully-connected layers.
problem Limited improvement in transfer learning accuracy with pre-trained models on small datasets.
method Re-Initializing fully-connected layers with random scratch during fine-tuning.
result Significant improvement in deep transfer learning accuracy across various datasets.
AOFP prunes CNN filters faster and more accurately.
problem Finding optimal CNN width and pruning filters efficiently.
method Binary search, random masking, multi-path framework.
result AOFP achieves faster pruning with minimal accuracy loss.
LeanConvNets reduces CNN costs without sacrificing accuracy.
problem High computational cost in fully-coupled CNNs.
method Sparsifying fully-coupled operators in CNNs.
result LeanConvNets achieve similar accuracy to state-of-the-art networks but with lower computational cost.
This paper provides an initial investigation on the application of convolutional neural networks (CNNs) for fingerprint-based positioning using measured massive MIMO channels. When represented in appropriate domains, massive MIMO channels have a sparse structure which can be efficiently learned by CNNs for positioning …
"How much energy is consumed for an inference made by a convolutional neural network (CNN)?" With the increased popularity of CNNs deployed on the wide-spectrum of platforms (from mobile devices to workstations), the answer to this question has drawn significant attention. From lengthening battery life of mobile device…
TentacleNet improves binarized CNNs, reducing accuracy loss and memory usage.
problem Excessive accuracy loss in binarized CNNs.
method Parallelization inspired by ensemble learning theory, end-to-end trainable compact topology.
result Significant memory savings compared to state-of-the-art binary ensemble methods.
The paper improves DFA for CNN and RNN training to match BP accuracy.
problem Low accuracy in CNN and RNN training using DFA.
method Divide network into modules, apply DFA within, use sparse backward weight, and incorporate dilated convolution and sparse matrix multiplication.
result Achieves BP-level accuracy in CNN and RNN training.
MobileNet CNN achieves high accuracy in skin disease classification on Android.
problem Skin disease classification using smartphone technology.
method Transfer learning on MobileNet, imbalanced dataset handling (sampling and preprocessing), and data augmentation.
result Oversampling and data augmentation on preprocessing input data achieved 94.4% accuracy.
Improved CNN with general image processing kernels reduces training time and achieves high accuracy.
problem Training time and accuracy of CNNs.
method Used 41 general-purpose kernels for the first layer of CNNs.
result GFNN reduces training time by 30% and achieves 99.56% accuracy.
Highly Accurate CNN Inference Using Approximate Activation Functions over Homomorphic Encryptioncs.LG
Improved CNN accuracy for encrypted data using approximate activation functions.
problem Low accuracy in classifying encrypted data using homomorphic encryption.
method Used a fourth-order polynomial approximation of the Swish activation function with batch normalization for homomorphic encryption.
result Achieved 99.22% accuracy on MNIST and 80.48% on CIFAR-10, improving by 0.04% and 4.11% respectively.
Machine Learning (ML) algorithms, like Convolutional Neural Networks (CNN), Support Vector Machines (SVM), etc. have become widespread and can achieve high statistical performance. However their accuracy decreases significantly in energy-constrained mobile and embedded systems space, where all computations need to be c…
Mixed-size training improves CNN accuracy and speed.
problem Training CNNs on fixed image sizes limits their adaptability to various image sizes.
method Mixed-size training: training on multiple image sizes at once.
result Models trained with mixed-size images achieve higher accuracy and faster inference.
Convolutional neural networks (CNNs) are similar to "ordinary" neural networks in the sense that they are made up of hidden layers consisting of neurons with "learnable" parameters. These neurons receive inputs, performs a dot product, and then follows it with a non-linearity. The whole network expresses the mapping be…
HOTCAKE compresses CNNs by decomposing kernels into smaller parts.
problem Compressing deep CNNs without significant accuracy loss.
method Input channel decomposition, guided Tucker rank selection, higher order Tucker decomposition, fine-tuning.
result HOTCAKE produces highly compressed CNN models with good accuracy.
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.
Boosting CNNs with dynamic feature selection and boosting weights improves accuracy and efficiency.
problem Expensive training of deep CNNs and manual architecture design.
method Dynamic feature selection, importance sampling, and boosting weights integrated into network training.
result Boosted CNN variants consistently outperform conventional CNNs in accuracy and training speed.
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 revisits graph-CNNs using Laplace-Beltrami spectral filters and polynomials.
problem Improving spectral graph convolutional neural networks (graph-CNNs).
method Developed Laplace-Beltrami CNN (LB-CNN) by replacing graph Laplacian with LB operator and approximating spectral filters using Chebyshev, Laguerre, and Hermite polynomials.
result Classification accuracy of LB-CNN is not dependent on the type of polynomials or operators.
We propose an extension of Convolutional Neural Networks (CNNs) to graph-structured data, including strided convolutions and data augmentation on graphs. Our method matches the accuracy of state-of-the-art CNNs when applied on images, without any prior about their 2D regular structure. On fMRI data, we obtain a signifi…
A CNN-based model improves stock price prediction accuracy.
problem Overfitting in image-based stock prediction models.
method SMSFR-CNN combining CNN and image features.
result SMSFR-CNN achieves high predictive accuracy on A-share stocks.
Computer vision performances have been significantly improved in recent years by Convolutional Neural Networks(CNN). Currently, applications using CNN algorithms are deployed mainly on general purpose hardwares, such as CPUs, GPUs or FPGAs. However, power consumption, speed, accuracy, memory footprint, and die size sho…
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.
LOCO-Reg improves CNN accuracy by promoting feature cohesion near filter centers.
problem Current regularization schemes in CNNs violate the principle that weights near the center of a filter are larger than weights on the outside.
method Introduces Locality-Promoting Regularization (LOCO-Reg) to correct this issue.
result LOCO-Reg yields accuracy gains across multiple architectures and datasets.
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.
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.
SCNN improves video object detection speed by 178%.
problem Limited throughput in existing CNNs for video object detection.
method Proposes SCNN, a statistical CNN that processes correlated distributions.
result Achieves 178% speedup over existing CNNs for video object detection.
This paper uses deep reinforcement learning to compress CNN models, reducing size and maintaining accuracy.
problem Reducing model size for efficient deployment on limited hardware resources.
method Two-stage compression pipeline: pruning and quantization using deep reinforcement learning.
result Significant reduction in model size with minimal loss in accuracy.
Achieving superhuman playing level by AlphaGo corroborated the capabilities of convolutional neural architectures (CNNs) for capturing complex spatial patterns. This result was to a great extent due to several analogies between Go board states and 2D images CNNs have been designed for, in particular translational invar…
This study compares two methods for uncertainty estimation in CNNs, finding Conformal Prediction more reliable.
problem CNNs often overestimate uncertainty, leading to unreliable predictions.
method Bayesian approximation via Monte Carlo Dropout and Conformal Prediction.
result Conformal Prediction produces more reliable uncertainty estimates than Monte Carlo Dropout.
Improved CNN training with BDFA reduces computational cost and improves accuracy.
problem Low training performance of DFA in CNN.
method Combining DFA with BP, introducing feedback weight initialization, and proposing BDFA.
result BDFA shows better performance than conventional BP, especially in small datasets.
Enhanced CNN kernels improve image classification accuracy.
problem Improving classification accuracy of CNNs.
method Local Average Pooling and random image patch representation.
result 89% accuracy on CIFAR-10, matching AlexNet performance.
NASirt automates CNN architecture design for spectral data.
problem Designing optimal neural architectures for complex data.
method Neural Architecture Search (NAS) with Item Response Theory (IRT) for instance-level complexity.
result NASirt achieves high accuracy (97.40%) on spectral datasets.
This work automates CNN model compression for mobile devices.
problem Deploying trained CNNs to mobile devices requires balancing speed, memory, and accuracy.
method Reinforcement learning with architecture search and knowledge distillation.
result An automated model compression algorithm improves the trade-off between speed, memory, and accuracy.
Study proposes CNN for reconstructing high-res urban DEMs.
problem Lack of high-res urban DEM datasets for flood modeling.
method Multi-scale CNN model trained on urban DEMs of varying resolutions.
result CNN-based method produces superior high-res urban DEMs.
Deep-learning CNN automates Cu alloy grain size evaluation.
problem Automating the evaluation of Cu alloy grain size to reduce labor and improve accuracy.
method Deep-learning convolutional neural network (CNN) for automated image acquisition and processing.
result Achieved 91.1% classification accuracy on Cu alloy sub-images.
A hybrid CNN with shared parameters learns to incorporate recurrent structures.
problem Designing efficient recurrent neural networks.
method Parameter sharing scheme combining CNN and recurrent layers.
result Substantial parameter savings with competitive accuracy.
S3NAS finds high-accuracy CNN architectures for NPUs in 3 hours.
problem Finding optimal CNN architectures for NPUs with high accuracy and low latency.
method Supernet design, Single-Path NAS, scaling, analytical latency estimation.
result 82.72% top-1 accuracy on ImageNet with 11.66 ms latency.