Compact convolution enhances CNN robustness against adversarial attacks.
problem Improving network robustness against adversarial attacks.
method Learning compact features using L2-Softmax Loss and compact convolution.
result Compact Convolutional Networks (CCNs) neutralize multiple types of adversarial attacks.
Compact bilinear pooling approximates covariance features for faster training.
problem Efficiently approximating covariance features for faster training.
method Compact bilinear pooling extended to polynomial approximations of covariance features.
result The proposed method achieves comparable accuracy with fewer dimensions.
Heating up softmax improves feature compactness for better metric learning.
problem Learning embeddings for samples of the same category to be compact while different categories spread out.
method Training classifiers with different temperature values of softmax function, then heating up the classifier.
result Classifier with increasing temperatures achieves state-of-the-art performance on metric learning benchmarks.
A new framework CL embeds features and labels for multi-label classification.
problem Exponential growth of output space in multi-label classification.
method Compact Learning (CL) framework that embeds features and labels simultaneously.
result CMLL maximizes label-feature dependency and minimizes label space loss.
Proposes a new CNN approach for multimodal biometric identification.
problem Improving biometric identification accuracy across multiple modalities.
method Uses a bank of modality-specific CNNs, fuses their outputs, and optimizes the system.
result Significantly outperforms unimodal systems and demonstrates reduction in parameters.
GOTabPFN improves tabular model performance with compact tokenization for HDLSS data.
problem Making tabular models effective for high-dimensional, low-sample size data without retraining.
method Introducing Graph-guided Ordering with Local Refinement (GO-LR) and Neuro-Inspired Subunit Compression (NSC) to create compact meta-features.
result GOTabPFN improves stability and accuracy in tabular benchmarks with compact tokenization.
Kernel approximation using randomized feature maps has recently gained a lot of interest. In this work, we identify that previous approaches for polynomial kernel approximation create maps that are rank deficient, and therefore do not utilize the capacity of the projected feature space effectively. To address this chal…
Unsupervised segmentation learns features without labels, improving accuracy.
problem Discover and localize semantically meaningful categories in images without annotations.
method Separates feature learning from cluster compactification; distills unsupervised features into discrete semantic labels using a contrastive loss function.
result Significant improvement over prior state of the art on semantic segmentation challenges.
Paper introduces template functions for featurizing persistence diagrams.
problem Featurizing persistence diagrams for machine learning.
method Characterizes compactness, constructs dense subsets of continuous functions.
result Template functions enable supervised learning with persistence diagrams.
Compact-CNN outperforms traditional methods in SSVEP classification.
problem Decoding SSVEPs without domain-specific knowledge.
method Compact convolutional neural network (Compact-CNN) for automatic feature extraction.
result Across subject mean accuracy of 80% (chance 8.3%) using Compact-CNN.
A novel feature representation method for non-image based features.
problem Inability of Convolutional Neural Networks for non-image based features or features without spatial correlations.
method REFINED: Representation of Features as Images with Neighborhood Dependencies.
result Higher prediction accuracy compared to existing methodologies.
Paper uses RL and DCAE to classify large unstructured data with fewer features.
problem Classifying large unstructured data with high precision using fewer features.
method Deep Convolutional Autoencoder (DCAE) for feature learning and Double DQN/Retrace RL algorithms for policy optimization.
result The approach achieves high classification precision with fewer features than traditional methods.
Study investigates classification with unknown label noise in non-compact feature spaces.
problem Classification in the presence of unknown class-conditional label noise in non-compact feature spaces.
method Determines minimax optimal learning rates and presents an adaptive algorithm for classification.
result Optimal learning rates differ from those without label noise, displaying interesting threshold behavior.
Optimal Coordinate Ascent (OCA) improves feature selection in machine learning.
problem Efficiently selecting features in machine learning models.
method Optimal Coordinate Ascent (OCA) for feature selection.
result OCA outperforms previous methods in feature selection and model performance.
Compact neural network for ECG classification reduces resource needs.
problem Current reliance on deep learning for ECG analysis requires extensive resources and large datasets.
method Simple ANN architecture with advanced feature engineering.
result Achieved 97.36% accuracy in classifying 4 types of arrhythmias.
MeliusNet improves binary neural networks to match MobileNet-v1 accuracy.
problem Achieving high accuracy with binary neural networks on mobile devices.
method Alternating DenseBlocks and ImprovementBlocks to increase feature capacity and quality.
result MeliusNet matches MobileNet-v1 accuracy on ImageNet, improving binary network performance.
VPFD uses vocoder features for adversarial training in VC.
problem Adversarial training on waveform data is time-consuming and memory-intensive.
method VPFD employs vocoder features for adversarial training.
result VPFD achieves VC performance comparable to waveform discriminators with reduced training time and memory.
Although the recent progress in the deep neural network has led to the development of learnable local feature descriptors, there is no explicit answer for estimation of the necessary size of a neural network. Specifically, the local feature is represented in a low dimensional space, so the neural network should have mo…
A novel online feature selection method using DPP for diversity.
problem Online feature selection for diverse feature sets.
method DPP-based framework with three stages: sampling, local criteria, and global criteria.
result Demonstrated better compactness and comparable/outsuperior performance.
Visualizes deep network feature contributions in images.
problem Understanding information flow in deep networks.
method Forward-Backward approach for feature visualization.
result Numerical results show benefits over existing methods.
Develops a new feature selection method using deep-learning saliency.
problem Lack of instance-level feature selection information.
method Saliency-based Feature Selection (SFS) method.
result SFS method provides instance-level feature selection information.
Compactness theorem for 3D RS-SW equations on 3-manifolds.
problem Non-compactness of moduli space of solutions.
method Variational approach to 3D RS-SW equations.
result Proof of compactness theorem.
Paper proves non-zero generalization boost for equivariant models.
problem Improving generalization in machine learning models.
method Analyzes simplest case of linear models, focusing on invariant/equivariant properties.
result First provably non-zero improvement in generalization for invariant/equivariant models.
Paper proposes angular loss for better face recognition and object classification.
problem Improving intra-class compactness and preventing overfitting in face recognition and object classification.
method Angular loss function to maximize angular gradient, reducing overfitting and requiring only one adjustable constant.
result Our method outperforms other methods in accuracy, discriminative information, and time-efficiency.
We prove that many features of Thurston's Dehn surgery theory for hyperbolic 3-manifolds generalize to Einstein metrics in any dimension. In particular, this gives large, infinite families of new Einstein metrics on compact manifolds.
SA-FDR uses simulated annealing for feature selection in high-dimensional data.
problem Feature selection in high-dimensional datasets with high predictive accuracy.
method Simulated Annealing for combinatorial optimisation of feature subsets.
result SA-FDR selects more compact feature subsets with high predictive accuracy.
Brain computer interfaces (BCI) enable direct communication with a computer, using neural activity as the control signal. This neural signal is generally chosen from a variety of well-studied electroencephalogram (EEG) signals. For a given BCI paradigm, feature extractors and classifiers are tailored to the distinct ch…
Proposes joint domain alignment and discriminative feature learning for deep domain adaptation.
problem Reduces domain shift and misclassification of target domain samples.
method Instance-based and center-based discriminative feature learning methods.
result Learning discriminative features in shared feature space significantly boosts deep domain adaptation performance.
Deep learning detects arrhythmia from RR-interval ECG data.
problem Diagnosing arrhythmia using ECG data.
method Convolutional neural network (CNN) on time-sliced RR-interval data.
result Compact system achieves accurate arrhythmia detection.
The main results of this article provide asymptotics at infinity of the Green's functions near and at the spectral gap edges for "generic" periodic second-order elliptic operators on noncompact Riemannian co-compact coverings with abelian deck groups. Previously, analogous results have been known for the case of $\math…
The asymptotic dimension theory was founded by Gromov in the early 90s. In this paper we give a survey of its recent history where we emphasize two of its features: an analogy with the dimension theory of compact metric spaces and applications to the theory of discrete groups.
As is well-known for compact Riemann surfaces, eigenvalues of the Laplacianbare distributed discretely and most of eigenvalues vary viewed as functions on the Teichmuller space. We discuss a new feature in the Lorentzian geometry, or more generally, in pseudo-Riemannian geometry. One of the distinguished features is th…
This work uses decision trees to encode relevant features and their interactions into neural networks, improving model performance.
problem Overfitting in neural networks with many irrelevant variables.
method Defines a mapping to encode decision tree extracted relationships into a neural network.
result The approach outperforms fully connected neural networks and tree-based methods.
Sparse random features improve accuracy in data-scarce settings.
problem Limited accuracy of random feature methods in data-scarce applications.
method Sparse random feature expansion using compressive sensing.
result Improved generalization bounds for sparse random features.
Modeling preference rankings with salient features to explain irrational choices.
problem Estimating rankings from noisy pairwise comparisons with irrational choices.
method Salient feature preference model with maximum likelihood estimation.
result Strong performance of maximum likelihood estimation on synthetic and real data.
We study solutions for the Hodge laplace equation Δu=ω on p forms with Lr estimates for r>1. Our main hypothesis is that Δ has a spectral gap in L2. We use this to get non classical Lr Hodge decomposition theorems. An interesting feature is …
Compact clustering in latent space improves semi-supervised learning.
problem Improving semi-supervised learning with unlabeled data.
method Dynamic graph creation over embeddings, label propagation, and Markov chain regularization.
result Compact clustering in latent space facilitates better separation and separation of labeled and unlabeled data.
Enhanced feature extraction pipeline boosts music genre recognition.
problem Improving music genre classification accuracy.
method Extended feature engineering pipeline with multiple stages and feedback loops.
result The method significantly improves classification performance on the GTZAN dataset.
Paper proposes a new method to learn features from error representations.
problem Learning from error representations in machine learning.
method Inverse feature learning (IFL) based on deep clustering.
result IFL leads to improved performance in classification and clustering.
In the first part of the paper we investigate some geometric features of Moser-Trudinger inequalities on complete non-compact Riemannian manifolds. By exploring rearrangement arguments, isoperimetric estimates, and gluing local uniform estimates via Gromov's covering lemma, we provide a Coulhon, Saloff-Coste and Varopo…
In this paper, we consider the joint task of simultaneously optimizing (i) the weights of a deep neural network, (ii) the number of neurons for each hidden layer, and (iii) the subset of active input features (i.e., feature selection). While these problems are generally dealt with separately, we present a simple regula…
Deep learning uses alphabet frequencies to accurately classify fake news.
problem Classifying fake news from trustworthy news.
method Used deep learning algorithms on alphabet frequencies of text without sequence information.
result Achieved high accuracy (85%) in classifying fake news.
CardiCat generates synthetic data for high-cardinality tabular datasets.
problem Learning complexities of high-cardinality categorical features in tabular data.
method Substitutes one-hot encoding with regularized dual encoder-decoder embedding layers.
result Generates high-quality synthetic data with a smaller parameter space.
The article constructs strong Carrollian geometries at infinity for Ricci flat Einstein manifolds.
problem Understanding projective and Carrollian geometries at infinity for Ricci flat Einstein manifolds.
method Developed a new type of Cartan geometry based on non-effective homogeneous models for projective geometry.
result Carrollian geometries are determined by the projective compactification data of Ricci flat Einstein manifolds.
Feature Quantization improves GAN training stability.
problem Stability issues in GAN training.
method Feature Quantization (FQ) for the discriminator, embedding true and fake data into a shared discrete space.
result FQ-GAN achieves new state-of-the-art performance on various GAN tasks.
Tactile information is important for gripping, stable grasp, and in-hand manipulation, yet the complexity of tactile data prevents widespread use of such sensors. We make use of an unsupervised learning algorithm that transforms the complex tactile data into a compact, latent representation without the need to record g…
Kernel methods benefit from enforcing invariance, reducing generalization error.
problem Improving generalization in kernel methods.
method Function space perspective and feature averaging for invariance.
result Strict non-zero generalization benefit for kernel ridge regression with invariant targets.
Tensor neural network improves human pose classification from 3D skeleton data.
problem Efficiently processing spatiotemporal data for human pose classification.
method Proposes a tensor-based neural network with three components: spatiotemporal feature construction, tensor fusion, and tensor-based neural network processing.
result Achieves state-of-the-art performance in human pose classification.