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.
Enhances CNN generalization in early learning with hierarchical transfer.
problem Improving CNN generalization in limited training time for real-time applications.
method Hierarchical transfer CNN framework combining shallow and cloud CNNs.
result Significant improvement in testing accuracy, up to 20% for CIFAR-10.
In image classification, visual separability between different object categories is highly uneven, and some categories are more difficult to distinguish than others. Such difficult categories demand more dedicated classifiers. However, existing deep convolutional neural networks (CNN) are trained as flat N-way classifi…
Tree-CNN adapts to new data by growing hierarchically.
problem Incremental learning for evolving datasets.
method Hierarchical deep convolutional neural network.
result Significant reduction in training effort with competitive accuracy.
Study on infinitely-wide CNNs and their adaptability to function spatial scales.
problem Understanding how CNNs efficiently learn high-dimensional functions and their adaptability to function spatial scales.
method Study infinitely-wide deep CNNs in the kernel regime, characterizing their spectrum and using generalisation bounds to prove adaptability.
result Deep CNNs adapt to the spatial scale of the target function, with error decay controlled by the effective dimensionality of function subsets.
Enhances image classification by integrating semantic hierarchy into CNN models.
problem Limited use of external guidance in image classification.
method Integrates label-hierarchy knowledge into CNN-based classifiers and uses order-preserving embeddings.
result Boosts image classification performance through semantic hierarchy integration.
Hierarchical CNNs improve diagnosis of GI diseases from histopathological images.
problem Diagnosing GI diseases from histopathological images is challenging due to heterogeneity and shared features.
method Embedded a class hierarchy into a VGGNet to address the hierarchical structure of GI diseases.
result The hierarchical model achieved better results than a flat model for multi-category diagnosis of GI disorders.
Proposes a novel framework for multi-label text classification.
problem Lack of coherent consideration of non-consecutive and long-distance semantics and hierarchical relations among labels.
method Hierarchical taxonomy-aware and attentional graph capsule recurrent CNNs framework.
result Significantly improves multi-label text classification performance.
SRHM explains deep learning's hierarchy and insensitivity to transformations.
problem Understanding how deep networks learn hierarchical and invariant representations.
method Introducing sparsity to generative hierarchical models of data.
result Hierarchical representations and insensitivity to transformations correlate strongly with deep network performance.
Proposes SimPool for graph pooling using structural similarity features.
problem Challenges in graph pooling due to lack of spatial locality.
method Integrates structural similarity features with a revised pooling layer to propose SimPool.
result SimPool produces node cluster assignments resembling CNN's locality preserving pooling.
A new framework combines CNN and GRU for better structural damage detection.
problem Improving damage detection in structural engineering using machine learning.
method Hierarchical CNN and Gated Recurrent Unit (GRU) framework to model spatial and temporal relations.
result The proposed HCG framework significantly outperforms existing methods for structural damage detection.
This work improves metric learning models by incorporating class hierarchies.
problem Class hierarchies are often ignored in classification-based metric learning models.
method Trained softmax classifier and metric learning models with predefined class hierarchies.
result ProxyDR model performs better in hierarchical inference and hierarchy-informed performance.
SplineNets improve CNNs by using continuous functions that can be conditioned on inputs.
problem Efficiency and accuracy trade-offs in CNNs.
method Continuous generalization of neural decision graphs using B-splines.
result SplineNets can significantly increase accuracy with minimal runtime cost.
New protocol benchmarks deep learning methods' data efficiency.
problem Measuring data efficiency of deep learning methods.
method Proposed experimental protocol to benchmark CNNs and HiGSFA.
result HiGSFA outperforms CNNs on smaller datasets.
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.
Develops visual explanations for Alzheimer's disease classification using 3D-CNNs.
problem Improving understanding of Alzheimer's disease classification using 3D-CNNs.
method Three approaches: sensitivity analysis and two activation visualization methods.
result Visual explanations identify important brain parts for Alzheimer's disease diagnosis.
Novel BCI system classifies imagined speech with high accuracy.
problem Classifying imagined speech from brain signals.
method Hierarchical deep learning with CNN and autoencoder.
result Achieved 83.42% average accuracy across six phonological tasks.
Spatial orderness metric improves CNN performance for non-spatial data.
problem Improving CNN performance for data lacking spatial order.
method Proposed spatial orderness metric to quantify spatial ordering.
result Adding convolutional layers is counterproductive for non-spatial data.
PETNet improves AD diagnosis using graph-based CNN on PET images.
problem Early diagnosis of Alzheimer's Disease using PET imaging.
method PETNet, a graph-based CNN architecture for 3D PET image analysis.
result PETNet shows improved performance over deep learning and other methods on ADNI dataset.
Convolutional Neural Networks (CNNs) are effective models for reducing spectral variations and modeling spectral correlations in acoustic features for automatic speech recognition (ASR). Hybrid speech recognition systems incorporating CNNs with Hidden Markov Models/Gaussian Mixture Models (HMMs/GMMs) have achieved the …
Distill-Net creates efficient CNNs for IoT by distilling complex models.
problem Efficient inference of deep CNNs on resource-constrained IoT platforms.
method Application-specific distillation of deep CNNs.
result Efficient inference on resource-constrained platforms with high accuracy.
Proposes a new learning framework for scalable image classification.
problem Scalability issues in CNN-based image classifiers for large number of classes.
method Combines hierarchical classification and auxiliary learning to address scalability issues.
result Reduces classification errors by up to 3.56% on CIFAR-10 dataset.
Transforms improve CNNs' invariance to image transformations.
problem Current CNN models lack robustness to spatial transformations.
method Randomly transform feature maps during training to learn invariant representations.
result Significant improvements on benchmark tasks, including image recognition and retrieval.
New model generates code from GUI screenshots using attention and hierarchical structure.
problem Challenges in converting abstract image features to code.
method Attention-based hierarchical decoder trained end-to-end.
result Model outperforms state-of-the-art methods on GUI-code datasets.
Deep CNN classifies EEG-based brain connectivity in schizophrenia.
problem Classifying neuropsychiatric disorders using EEG connectivity.
method Multi-domain connectome CNN framework integrating time and frequency-domain metrics.
result MDC-CNN achieves 93.06% accuracy in schizophrenia classification. The paper explains implicit regularization in hierarchical tensor factorization and deep CNNs.
problem Understanding implicit regularization in complex neural network architectures.
method Theoretical analysis using dynamical systems to overcome challenges in hierarchy.
result Established implicit regularization towards low hierarchical tensor rank, equivalent to locality in CNNs.
This paper proposes a new method to compress CNNs for medical image analysis, improving efficiency and accuracy.
problem Large memory and computational requirements of CNNs in resource-constrained environments.
method Hierarchical spatio-channel low-rank compression framework that partitions feature maps into spatial regions and groups channels according to co-activation patterns within each region.
result The proposed method achieves significant FLOP reduction, inference speed-up, and improved classification accuracy compared to existing methods.
Mixed DNN approach improves EEG-based speech imagery recognition.
problem Automatic identification of imagined speech from EEG.
method Hierarchical deep neural network strategy combining CNN, RNN, and autoencoders.
result 23.45% improvement in accuracy over baseline method.
Smooth kernel regularizer improves deep neural networks' performance with less data.
problem Deep neural networks need large datasets for effective learning.
method Proposes a smooth kernel regularizer that encourages spatial correlations in convolution kernel weights, learned from previous experience.
result The smooth kernel regularizer improves visual recognition models over an L2 regularization baseline.
CapsAttacks study imperceptible adversarial attacks on Capsule Networks, showing they can fool these networks.
problem Vulnerability of Capsule Networks to imperceptible adversarial attacks.
method Proposed a greedy algorithm for generating targeted imperceptible adversarial examples.
result Capsule Networks can be fooled by imperceptible adversarial attacks, similar to CNNs.
The thesis introduces methods to use semantic hierarchy in image classification.
problem Limited work in training image classifiers with non-conventional external guidance.
method Injects label hierarchy knowledge into arbitrary classifiers and uses order-preserving embeddings for image classification.
result Both embedding-based models and CNN-classifiers with hierarchical information outperform a hierarchy-agnostic model.
Sparse hierarchical graph classification improves graph-based benchmarks.
problem Sparse hierarchical graph classification challenges.
method Combining recent advances in graph neural network design, differentiable graph coarsening, and sparse pooling.
result Competitive hierarchical graph classification results possible without sacrificing sparsity.
Proposes a deep learning model for predicting traffic speeds in real-time.
problem Difficulty in capturing traffic data's random, seasonal, non-linear, and spatio-temporal correlated nature.
method Hierarchical D-CLSTM-t model combining CNN and LSTM for short-term traffic speed prediction.
result D-CLSTM-t model outperforms other models in predicting traffic speeds.
Robotic table tennis learns efficient policies to return balls at 100Hz.
problem Developing efficient robotic table tennis strategies.
method Model-free reinforcement learning using evolutionary search on CNN-based policies.
result Robots can develop multi-modal styles (forehand and backhand) with 80% return rate.
Novel channel pruning method accelerates deep CNNs by removing redundant, similar features.
problem Limitations of existing magnitude-based pruning algorithms in similar magnitude cases.
method Hierarchical clustering of channels based on probabilistic similarity metrics, without sparsity training.
result 30% reduction in FLOPs for pruned ResNet-50 on ImageNet, outperforming baseline.
Deep CNN models improve spatio-temporal forecasting efficiency.
problem Efficiently forecasting spatio-temporal dynamics with realistic models.
method Hierarchical statistical IDE framework with CNN for dynamic extraction.
result CNN provides accurate, interpretable, and computationally efficient forecasts.
Study identifies COVID-19 pneumonia from chest X-rays.
problem Identifying COVID-19 pneumonia from other types and healthy lungs using CXR images.
method Proposed a multi-class and hierarchical classification schema using CXR images, texture descriptors, and a pre-trained CNN model. Employed resampling algorithms and early/late fusion techniques.
result Achieved macro-avg F1-Score of 0.65 and F1-Score of 0.89 for COVID-19 identification in hierarchical classification scenario.
We introduce the hierarchical compositional network (HCN), a directed generative model able to discover and disentangle, without supervision, the building blocks of a set of binary images. The building blocks are binary features defined hierarchically as a composition of some of the features in the layer immediately be…
AutoQ automatically optimizes quantization for CNNs, reducing latency and energy.
problem Efficiently quantizing CNN weights for low-power mobile devices.
method Hierarchical-DRL for kernel-wise quantization bitwidth selection.
result Reduces inference latency and energy consumption by 54.06% and 50.69% respectively.
UAG defends GNNs against adversarial attacks by quantifying and explaining uncertainties.
problem Lack of uncertainty quantification in GNNs makes them vulnerable to adversarial attacks.
method UAG uses Bayesian Uncertainty Technique (BUT) and Uncertainty-aware Attention Technique (UAT).
result UAG outperforms state-of-the-art solutions in defending adversarial attacks on GNNs.
SKN learns multi-layer nonlinear features using kernel methods.
problem Limited representational power of classic kernel methods.
method Interleaves layers of nonlinear and linear transformations in a hierarchy of RKHS-based features.
result SKN and SKCN outperform competitive methods on various datasets.
Deep model forecasts correlated multivariate time series.
problem Forecasting correlated multivariate time series.
method Deep learning structural model using CNN-LSTM architecture.
result Model outperforms state-of-the-art methods in various time series data sets.
New approach predicts generalization of deep neural networks in proportional-width regime.
problem Predicting generalization of deep neural networks in proportional-width regime.
method Equivalent Wishart Ansatz for hierarchical empirical kernels, renormalized NNGP kernel.
result Renormalized NNGP kernel captures dominant stochastic fluctuations in deep neural networks.
OmicsMapNet converts omics data into 2D images for deep learning analysis.
problem Analyzing high-dimensional omics data for phenotype classification.
method Reorganize omics data into 2D images, apply deep learning to classify, identify key features.
result Deep learning models accurately classify TCGA glioma samples based on molecular features.
PFPN improves salient object detection by progressively polishing multi-level features.
problem Improving salient object detection by refining multi-level features.
method Progressive Feature Polishing Network (PFPN) with Feature Polishing Modules (FPMs).
result PFPN achieves superior performance on five benchmark datasets without post-processing.
CycleGAN-VC converts speech without parallel data, achieving high quality.
problem Voice conversion without parallel data.
method Cycle-Consistent Adversarial Networks (CycleGAN) with gated CNNs and identity-mapping loss.
result Converted speech quality comparable to Gaussian mixture model-based methods under advantageous conditions.
Sublinearly structured DNNs achieve feature learning consistency for compositional functions.
problem Achieving feature-learning and prediction consistency in deep neural networks.
method Sublinearly structured DNNs
result Sublinearly structured DNNs match or surpass wide DNNs in prediction.
New principle reveals how neural networks learn complex interactions.
problem Understanding neural networks' success and complexity.
method Infinite-width networks, focusing on frequency and space.
result Fine-grained eigenstructure improves network learnability.