In recent years, deep learning poses a deep technical revolution in almost every field and attracts great attentions from industry and academia. Especially, the convolutional neural network (CNN), one representative model of deep learning, achieves great successes in computer vision and natural language processing. How…
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”
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.
Efficient CNN for VQA achieves similar performance to standard models.
problem Computational intensity of standard VQA models.
method Proposes a sparsely activated CNN architecture.
result Sparsely activated CNN achieves comparable performance.
CNN model predicts fluvial floods quickly and accurately.
problem Real-time flood prediction is computationally demanding.
method Deep Convolutional Neural Network (CNN) trained on 2D hydraulic model outputs.
result CNN model outperforms SVR in predicting flood inundation.
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.
New CNN layer selects important channels to improve model capacity.
problem Improving model capacity under resource constraints.
method Selective allocation of channels in convolutional layers.
result New layer allows new optima that generalize better.
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…
Automates resource-efficient CNN design for IoT.
problem Designing custom CNNs for IoT applications is impractical and resource-intensive.
method Automated synthesis of resource scalable CNNs from an existing optimized baseline CNN.
result Synthesized CNNs are resource-efficient and competitive in accuracy.
New CNN initialization scheme derived from modern architectures.
problem Stability of CNN model parameters initialization.
method Derived new initialization scheme from modern CNN architectures.
result New initialization method outperforms de facto standard schemes.
iSTFTNet2 improves iSTFTNet's speed and lightness with 1D-2D CNN.
problem Efficiently synthesizing high-fidelity speech.
method Improved iSTFTNet using 1D-2D CNNs for temporal and spectrogram structures.
result iSTFTNet2 is faster and more lightweight with comparable speech quality.
Ego-CNN detects critical structures in graphs efficiently.
problem Lack of precise detection of critical structures in existing graph embedding models.
method Ego-CNN uses ego-convolutions at each layer and stacks them in an ego-centric way.
result Ego-CNN achieves comparable task performance to state-of-the-art models and can incorporate scale-free priors.
CNNs improve medical image classification with few samples.
problem Classifying medical images with limited training data.
method Transfer learning using CNNs, representation extraction, and a novel metric for performance prediction.
result CNN-based transfer learning outperforms feature-based methods with high correlation to test set performance.
This paper introduces a new measure to identify model redundancy in compressed CNNs.
problem Identifying remaining model redundancy in compressed CNNs.
method Developed a statistical formulation of CNNs and compressed CNNs via tensor decomposition, revealing discrepancies in sample complexity and model redundancy.
result Introduced a new model redundancy measure, the ratio, for compressed CNNs.
Can a CNN trained on the Ising model detect the phase transition of the -state Potts model?cond-mat.dis-nn
CNN detects phase transitions in Potts models without prior knowledge.
problem Detecting phase transitions in -state Potts models using deep learning.
method Trained a deep CNN on Ising model spin configurations and temperatures, then tested on Potts model images.
result Deep CNN accurately detects phase transitions in Potts models, including high- and low-temperature regions.
2D CNNs approximate Korobov functions with near-optimal rates.
problem Approximating Korobov functions using 2D CNNs.
method Constructive approach for 2D CNNs with ReLU activations and fully connected layers.
result 2D CNNs achieve near-optimal approximation rates for Korobov functions.
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.
TinyCNN accelerates CNN models on embedded FPGA with 15x speedup.
problem Limited memory on embedded FPGAs restricts CNN performance.
method Software and hardware design tool for FPGA resource-aware CNN accelerator.
result 3% accuracy loss with 15.75x speedup on image classification.
FixyNN splits CNN models into fixed and trainable parts for efficient on-device inference.
problem Energy inefficiency in on-device CNN inference for real-time computer vision.
method Co-designed hardware accelerator platform with transfer learning for training.
result Achieved nearly 2x better energy efficiency than a conventional accelerator.
Combines CNN and RNN for hierarchical image classification.
problem Hierarchical relations between image categories are not captured by flat classifiers.
method Uses a CNN for feature extraction and an RNN for capturing hierarchical class relations. Incorporates residual learning.
result Hierarchical networks outperform state-of-the-art CNNs on a real-world dataset.
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.
Split learning preserves privacy in 1D CNN models for detecting heart abnormalities.
problem Privacy leakage in 1D CNN models under split learning.
method Implemented and validated an 1D CNN model under split learning, applied privacy leakage mitigation techniques.
result Split learning alone is insufficient to maintain raw data privacy in 1D CNN models.
Deep learning improves GW signal detection efficiency and robustness.
problem Traditional matched-filtering techniques are limited in detecting new GW signals.
method Optimized CNN models with techniques like batch normalization and dropout.
result CNN models are robust to the variation of GW waveform parameters.
Convolutional neural networks (CNNs) are one of the driving forces for the advancement of computer vision. Despite their promising performances on many tasks, CNNs still face major obstacles on the road to achieving ideal machine intelligence. One is that CNNs are complex and hard to interpret. Another is that standard…
CNN-LSTM models for Multi-Speaker Source Separation using Bayesian Hyper Parameter Optimizationcs.LG
Paper proposes CNN-LSTM model for multi-speaker speech separation.
problem Multi-speaker source separation using deep learning.
method Parallel CNN-LSTM architecture with Bayesian hyperparameter optimization.
result Parallel CNN-LSTM model outperforms LSTM-only and CNN-only models.
Paper investigates trade-off between video bitrate and CNN accuracy.
problem Network bandwidth and energy consumption issues in video classification.
method Only retain motion vector and select texture information at reduced bitrates.
result Achieved 11%-94% saving in bitrate with marginal accuracy loss.
New CNN method improves deconvolution microscopy without PSF measurement.
problem Computational expense and blind estimation in conventional deconvolution microscopy.
method Cycle consistent CNN with explicit PSF modeling layers for blind deconvolution.
result Algorithm robustness and efficacy confirmed through experimental results.
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.
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.
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.
Generative model attacks CNN on MNIST by subtly replacing input patterns.
problem Adversarial attacks on neural networks.
method Generative model that replaces input patterns with generated ones.
result Demonstrated effectiveness on MNIST dataset.
A CNN integrates with Markov random fields for brain segmentation.
problem Combining CNNs and probabilistic models for robust brain segmentation.
method Backpropagation-based recurrent CNN for spatial interactions in Markov random fields.
result Model generalizes across different imaging protocols.
New metrics differentiate effective OOD sets for training calibrated CNNs.
problem Vanilla CNNs struggle with out-of-distribution (OOD) samples.
method Developed metrics based on generalization errors of Augmented-CNN.
result Most protective OOD sets lead to better A-CNN performance.
CNNs show sensitivity to low-frequency signals due to image frequency distribution.
problem Understanding why CNNs are sensitive to low-frequency signals.
method Theoretical analysis of CNN representations in frequency space.
result CNNs sensitivity to low-frequency signals is due to the frequency distribution of natural images.
Paper presents a light-weight CNN model for Parkinson's disease diagnosis.
problem Diagnosing Parkinson's disease efficiently and accurately.
method A light-weight CNN model cascading to LSTM for time-series signals.
result The model achieves high-quality results with fewer parameters and operations.
Developed AI models for multi-gas detection in near IR spectrums.
problem Detecting multiple gases in near IR spectrums.
method Used Monte Carlo KNN and multi-resolution CNN, synthesized near IR spectrums, optimized kernel sizes and channels.
result Multi-resolution CNN outperforms other models.
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.
A CNN-DRL model improves learning in finance with scalable actions.
problem Finance environments with large action scales are hard for MLP-based DRL agents.
method Designed a CNN agent that uses historical data to adapt to large action scales.
result The CNN-DRL model remains stable and learns the environment better than MLP.
CNN improves spatiotemporal emotion recognition from EEG during music listening.
problem Improving emotion recognition from EEG signals during music listening.
method Conducted a study on CNN and its spatiotemporal feature extraction for emotion recognition.
result CNN outperforms SVM in leave-one-subject-out cross validation.
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.
Unified method for CNNs to approximate equivariant maps across various groups.
problem Limited universal approximation theorems for CNNs with specific groups and settings.
method Unified approach to derive universal approximation theorems for equivariant maps by CNNs in diverse settings.
result Ability to handle non-linear equivariant maps between infinite-dimensional spaces for non-compact groups.
Paper attacks CNNs in EEG BCIs with adversarial examples.
problem Vulnerability of CNN classifiers in EEG-based BCIs.
method UFGSM to attack three popular CNN classifiers in BCIs.
result Demonstrates effectiveness of adversarial attacks on CNNs in BCIs.
Survey on pruning CNN models to reduce size for edge devices.
problem Reducing large CNN models for edge deployment.
method Comprehensive review of pruning strategies, criteria, and techniques.
result Pruning accelerates CNN models for edge applications.
L-CNNs preserve gauge symmetry in lattice simulations.
problem Breaking gauge symmetry in neural network models.
method Lattice gauge equivariant convolutional neural networks (L-CNNs).
result L-CNNs represent gauge invariant functions on the lattice.
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…
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 …
The adaptability of the convolutional neural network (CNN) technique for aerodynamic meta-modeling tasks is probed in this work. The primary objective is to develop suitable CNN architecture for variable flow conditions and object geometry, in addition to identifying a sufficient data preparation process. Multiple CNN …
When deep learning models on GPU can be accelerated by taking advantage of unstructured sparsitycs.LG
This paper accelerates sparse CNN layers on GPUs by using unstructured sparsity.
problem Efficiency of sparse CNN layers on GPUs.
method Direct sparse operation and reduced precision.
result Achieving up to 90% sparsity in deep CNN models improves efficiency.
Inspired by recent advances in deep learning, we propose a novel iterative BP-CNN architecture for channel decoding under correlated noise. This architecture concatenates a trained convolutional neural network (CNN) with a standard belief-propagation (BP) decoder. The standard BP decoder is used to estimate the coded b…