arXiv research

Develops a robust multiclass classification method for deep image classifiers.

Top-k error is currently a popular performance measure on large scale image classification benchmarks such as ImageNet and Places. Despite its wide acceptance, our understanding of this metric is limited as most of the previous research is focused on its special case, the top-1 error. In this work, we explore two direc…

We propose a learning algorithm capable of learning from label proportions instead of direct data labels. In this scenario, our data are arranged into various bags of a certain size, and only the proportions of each label within a given bag are known. This is a common situation in cases where per-data labeling is lengt…

In this paper, we tackle the question of discovering an effective set of spatial filters to solve hyperspectral classification problems. Instead of fixing a priori the filters and their parameters using expert knowledge, we let the model find them within random draws in the (possibly infinite) space of possible filters…

Proposes sigmoidF1 loss for multilabel classification, improving performance metrics.

Unified binary and multiclass margin-based classification methods.

Class ambiguity is typical in image classification problems with a large number of classes. When classes are difficult to discriminate, it makes sense to allow k guesses and evaluate classifiers based on the top-k error instead of the standard zero-one loss. We propose top-k multiclass SVM as a direct method to optimiz…

BraidNet uses braid theory to optimize neural networks for image classification.

Robotic weed control has seen increased research of late with its potential for boosting productivity in agriculture. Majority of works focus on developing robotics for croplands, ignoring the weed management problems facing rangeland stock farmers. Perhaps the greatest obstacle to widespread uptake of robotic weed con…

The paper analyzes how overparameterized models can generalize well in multiclass classification.

Proposes MCLLO for assessing and recalibrating multiclass probability predictions.

New research determines the optimal sample complexity for multiclass and list learning.

Study shows exponential error reduction in multiclass classification without bias-variance trade-off.

Establishes a condition for multiclass classification-calibration of Gamma-Phi losses.

New reformulations for multiclass classification problems using optimal transport.

Paper studies multiclass classifiers from binary classifiers, proving methods and demonstrating advantages.

This work extends implicit bias analysis to multiclass classification using a new loss framework.

New method for multiclass classification reduces error bounds.

Algorithm minimizes risk for multiclass classification of stochastic diffusion paths.

Pre-trained word embeddings encode general word semantics and lexical regularities of natural language, and have proven useful across many NLP tasks, including word sense disambiguation, machine translation, and sentiment analysis, to name a few. In supervised tasks such as multiclass text classification (the focus of …

Study online multiclass classification under bandit feedback, extending previous results.

We study a multiclass multiple instance learning (MIL) problem where the labels only suggest whether any instance of a class exists or does not exist in a training sample or example. No further information, e.g., the number of instances of each class, relative locations or orders of all instances in a training sample, …

Extends boosting to multiclass online agnostic classification.

Study proves existence of robust classifiers in multiclass adversarial training.

We propose a robust adversarial prediction framework for general multiclass classification. Our method seeks predictive distributions that robustly optimize non-convex and non-continuous multiclass loss metrics against the worst-case conditional label distributions (the adversarial distributions) that (approximately) m…

Paper analyzes multiclass classification with high-dimensional data.

New algorithm improves multiclass classification regret bound.

Improved graph-based multiclass classification for multilayer data.

We present two graph-based algorithms for multiclass segmentation of high-dimensional data. The algorithms use a diffuse interface model based on the Ginzburg-Landau functional, related to total variation compressed sensing and image processing. A multiclass extension is introduced using the Gibbs simplex, with the fun…

New binary classification techniques help multiclass classification by aggregating proper learners.

Develops a functional mix-of-experts model for multiclass classification.

New research shows SVM and related methods can overfit without harm in multiclass classification.

Combining Bayesian deep learning and split conformal prediction affects out-of-distribution coverage.

Binary and multiclass epilepsy detection methods using EEG features.

Gaptron algorithm reduces mistakes in online multiclass classification.

Develops NPMC method for noisy labels, improving multiclass classification accuracy.

Improved multiclass classification with class-weighted nearest neighbors.

Ideas from the image processing literature have recently motivated a new set of clustering algorithms that rely on the concept of total variation. While these algorithms perform well for bi-partitioning tasks, their recursive extensions yield unimpressive results for multiclass clustering tasks. This paper presents a g…

Unified SVM framework tackles multiclass and multilabel classification.

Study expands multiclass classification models with new rates and partial concept classes.

Study optimal rates for multiclass classification, resolving open questions.

Paper tackles noisy bandit feedback for multiclass classification.

Study builds a classifier for diffusions with unknown diffusion but known drifts.

This work analyzes label embedding for large multiclass classification problems.

One-bit quantization and sparsification improve multiclass classification with strong regularization.

Sparse multinomial logistic regression for multiclass classification with feature selection.

New bounds show agnostic multiclass learning depends on two dimensions: Natarajan and Daniely-Shalev-Shwartz.

New algorithm learns multiclass concepts with finite Littlestone dimension.