Related papers: Massively Scaling Heteroscedastic Classifiers
Supervised contrastive learning (SCL) frameworks treat each class as independent and thus consider all classes to be equally important. This neglects the common scenario in which label hierarchy exists, where fine-grained classes under the…
We develop a new edge detection algorithm that tackles two important issues in this long-standing vision problem: (1) holistic image training and prediction; and (2) multi-scale and multi-level feature learning. Our proposed method,…
Deep learning (DL) algorithms are the state of the art in automated classification of wildlife camera trap images. The challenge is that the ecologist cannot know in advance how many images per species they need to collect for model…
Contrastive learning is a discriminative approach that aims at grouping similar samples closer and diverse samples far from each other. It it an efficient technique to train an encoder generating distinguishable and informative…
Generalized zero-shot learning (GZSL) aims to recognize objects from both seen and unseen classes, when only the labeled examples from seen classes are provided. Recent feature generation methods learn a generative model that can synthesize…
A principle bottleneck in image classification is the large number of training examples needed to train a classifier. Using active learning, we can reduce the number of training examples to teach a CNN classifier by strategically selecting…
Convolutional neural networks and supervised learning have achieved remarkable success in various fields but are limited by the need for large annotated datasets. Few-shot learning (FSL) addresses this limitation by enabling models to…
To facilitate implementation of high-accuracy deep neural networks especially on resource-constrained devices, maintaining low computation requirements is crucial. Using very deep models for classification purposes not only decreases the…
In this paper, a high-speed online neural network classifier based on extreme learning machines for multi-label classification is proposed. In multi-label classification, each of the input data sample belongs to one or more than one of the…
Conventional event detection models under supervised learning settings suffer from the inability of transfer to newly-emerged event types owing to lack of sufficient annotations. A commonly-adapted solution is to follow a…
The Potts model is frequently used to describe the behavior of image classes, since it allows to incorporate contextual information linking neighboring pixels in a simple way. Its isotropic version has only one real parameter beta, known as…
The problem of detecting change points in the parameters of a linear regression model with errors and covariates exhibiting heteroscedasticity is considered. Asymptotic results for weighted functionals of the cumulative sum (CUSUM)…
One of the roadblocks for training generalist robotic models today is heterogeneity. Previous robot learning methods often collect data to train with one specific embodiment for one task, which is expensive and prone to overfitting. This…
It is not uncommon that real-world data are distributed with a long tail. For such data, the learning of deep neural networks becomes challenging because it is hard to classify tail classes correctly. In the literature, several existing…
Semi-supervised learning aims to boost the accuracy of a model by exploring unlabeled images. The state-of-the-art methods are consistency-based which learn about unlabeled images by encouraging the model to give consistent predictions for…
Extreme multi-label learning (XML) or classification has been a practical and important problem since the boom of big data. The main challenge lies in the exponential label space which involves $2^L$ possible label sets especially when the…
Few-shot image classification aims to classify unseen classes with limited labelled samples. Recent works benefit from the meta-learning process with episodic tasks and can fast adapt to class from training to testing. Due to the limited…
Via an overparameterized linear model with Gaussian features, we provide conditions for good generalization for multiclass classification of minimum-norm interpolating solutions in an asymptotic setting where both the number of underlying…
Graphs are powerful representations for relations among objects, which have attracted plenty of attention. A fundamental challenge for graph learning is how to train an effective Graph Neural Network (GNN) encoder without labels, which are…
Hyperdimensional computing (HDC) is a promising approach for energy-efficient edge machine learning (ML), where low latency, low power, and tight memory budgets are essential. However, traditional HDC relies on symbolic binding and…