arXiv research

This paper proposes a novel generic one-class feature learning method based on intra-class splitting. In one-class classification, feature learning is challenging, because only samples of one class are available during training. Hence, state-of-the-art methods require reference multi-class datasets to pretrain feature …

Contrastive learning struggles with class collapse and feature suppression, revealing bias towards simpler solutions.

In this paper, a novel feature selection method is presented, which is based on Class-Separability (CS) strategy and Data Envelopment Analysis (DEA). To better capture the relationship between features and the class, class labels are separated into individual variables and relevance and redundancy are explicitly handle…

Optimizes feature shifts for tree ensemble reclassification.

XNB classifier improves model interpretability by selecting class-specific features.

The paper addresses over-fitting in deep learning models trained on imbalanced data.

Mixup helps learn both features in multi-view classification problems.

This paper introduces a new feature learning technique based on error representation.

Paper tackles class-incremental time series classification with dual-stream feature extraction.

This paper extends neural collapse to class-imbalanced datasets using an unconstrained ReLU feature model.

In this letter, we present a novel exponentially embedded families (EEF) based classification method, in which the probability density function (PDF) on raw data is estimated from the PDF on features. With the PDF construction, we show that class-specific features can be used in the proposed classification method, inst…

DSAEE FS selects features for imbalanced data.

Neural collapse occurs in normalized features over a Riemannian manifold.

SQFA learns features maximizing Fisher-Rao distance for better classification.

Study reveals class-dependent effects in perturbation-based feature attribution metrics for time series classification.

Directly compute classification by learning features with class scores.

The study sets lower bounds on MMSE for inferring sensitive features from noisy data.

Deep neural networks trained over large datasets learn features that are both generic to the whole dataset, and specific to individual classes in the dataset. Learned features tend towards generic in the lower layers and specific in the higher layers of a network. Methods like fine-tuning are made possible because of t…

Optimal transport framework for zero-shot learning.

Proposes a method for clearer counterfactual explanations of deep networks.

Herein, we generate pseudo-features based on the multivariate probability distributions obtained from the feature maps in layers of trained deep neural networks. Further, we augment the minor-class data based on these generated pseudo-features to overcome the imbalanced data problems. The proposed method, i.e., cavity …

The study reveals how adversarial perturbations can include class features for generalization.

Recently, considerable effort has been devoted to deep domain adaptation in computer vision and machine learning communities. However, most of existing work only concentrates on learning shared feature representation by minimizing the distribution discrepancy across different domains. Due to the fact that all the domai…

Conventional mutual information (MI) based feature selection (FS) methods are unable to handle heterogeneous feature subset selection properly because of data format differences or estimation methods of MI between feature subset and class label. A way to solve this problem is feature transformation (FT). In this study,…

Multiclass prediction is the problem of classifying an object into a relevant target class. We consider the problem of learning a multiclass predictor that uses only few features, and in particular, the number of used features should increase sub-linearly with the number of possible classes. This implies that features …

Improves few-shot learning for hierarchical data using hyperbolic space.

This paper proposes a zero-shot learning approach for audio classification based on the textual information about class labels without any audio samples from target classes. We propose an audio classification system built on the bilinear model, which takes audio feature embeddings and semantic class label embeddings as…

CDF uses centroids to split features for high-dimensional classification.

Random feature approximation speeds up spectral methods and improves learning rates.

The objective of the paper is to study accuracy of multi-class classification in high-dimensional setting, where the number of classes is also large ("large $L$, large $p$, small $n$" model). While this problem arises in many practical applications and many techniques have been recently developed for its solution, to t…

A new model SEQ clusters and classifies encoded features for better interpretability.

OCCER uses regression models to classify data points as outliers.

We characterize the class of exchangeable feature allocations assigning probability $V_{n,k}\prod_{l=1}^{k}W_{m_{l}}U_{n-m_{l}}$ to a feature allocation of $n$ individuals, displaying $k$ features with counts $(m_{1},\ldots,m_{k})$ for these features. Each element of this class is parametrized by a countable matrix $V$…

New algorithms identify invariant features for domain generalization.

Objective: A variety of pattern analysis techniques for model training in brain interfaces exploit neural feature dimensionality reduction based on feature ranking and selection heuristics. In the light of broad evidence demonstrating the potential sub-optimality of ranking based feature selection by any criterion, we …

At present, object recognition studies are mostly conducted in a closed lab setting with classes in test phase typically in training phase. However, real-world problem is far more challenging because: i) new classes unseen in the training phase can appear when predicting; ii) discriminative features need to evolve when…

HGNN learns augmented features for deep multi-task learning.

New model combines shape and feature-based measures for better time series classification.

CFA improves model's ability to generalize across unseen domain-class combinations.

Proposes a new framework for EEG-based BCIs without adversarial learning.

SJS model predicts label shifts in multinomial datasets.

ICAM creates interpretable feature attribution maps for brain images.

A new method for adapting to label shifts using class probability matching.

Unsupervised clustering can reproduce categorization systems if features and metrics are correctly selected.

This paper extends neural collapse to imbalanced data under cross-entropy loss.

This study addresses an issue of co-adaptation between a feature extractor and a classifier in a neural network. A naive joint optimization of a feature extractor and a classifier often brings situations in which an excessively complex feature distribution adapted to a very specific classifier degrades the test perform…

In this paper, we focus on the separability of classes with the cross-entropy loss function for classification problems by theoretically analyzing the intra-class distance and inter-class distance (i.e. the distance between any two points belonging to the same class and different classes, respectively) in the feature s…

The high dimensionality of hyperspectral images often results in the degradation of clustering performance. Due to the powerful ability of deep feature extraction and non-linear feature representation, the clustering algorithm based on deep learning has become a hot research topic in the field of hyperspectral remote s…