相关论文: MaxSup: Overcoming Representation Collapse in Labe…

Label smoothing is a widely studied regularization technique in machine learning. However, its potential for node classification in graph-structured data, spanning homophilic to heterophilic graphs, remains largely unexplored. We introduce…

Deep neural networks have shown impressive performance in supervised learning, enabled by their ability to fit well to the provided training data. However, their performance is largely dependent on the quality of the training data and often…

Contrastive learning (CL) has emerged as a powerful technique for representation learning, with or without label supervision. However, supervised CL is prone to collapsing representations of subclasses within a class by not capturing all…

Minimizing prediction uncertainty on unlabeled data is a key factor to achieve good performance in semi-supervised learning (SSL). The prediction uncertainty is typically expressed as the \emph{entropy} computed by the transformed…

Image classification datasets exhibit a non-negligible fraction of mislabeled examples, often due to human error when one class superficially resembles another. This issue poses challenges in supervised contrastive learning (SCL), where the…

To train robust deep neural networks (DNNs), we systematically study several target modification approaches, which include output regularisation, self and non-self label correction (LC). Two key issues are discovered: (1) Self LC is the…

The Mixup scheme suggests mixing a pair of samples to create an augmented training sample and has gained considerable attention recently for improving the generalizability of neural networks. A straightforward and widely used extension of…

Given a family of linear constraints and a linear objective function one can consider whether to apply a Linear Programming (LP) algorithm or use a Linear Superiorization (LinSup) algorithm on this data. In the LP methodology one aims at…

Pseudo-labeling is a commonly used paradigm in semi-supervised learning, yet its application to semi-supervised regression (SSR) remains relatively under-explored. Unlike classification, where pseudo-labels are discrete and confidence-based…

The impressive growth of data throughput in optical microscopy has triggered a widespread use of supervised learning (SL) models running on compressed image datasets for efficient automated analysis. However, since lossy image compression…

Deep vision classifiers often achieve high accuracy while remaining poorly calibrated and fragile under small distribution shifts. We present Margin and Consistency Supervision (MaCS), a simple, architecture-agnostic regularization…

It is not an exaggeration to say that the recent progress in artificial intelligence technology depends on large-scale and high-quality data. Simultaneously, a prevalent issue exists everywhere: the budget for data labeling is constrained.…

Spoken language understanding (SLU) datasets, like many other machine learning datasets, usually suffer from the label imbalance problem. Label imbalance usually causes the learned model to replicate similar biases at the output which…

Pretraining large language models (LLMs) with next-token prediction has led to remarkable advances, yet the context-dependent nature of token embeddings in such models results in high intra-class variance and inter-class similarity, thus…

Noisy labels damage the performance of deep networks. For robust learning, a prominent two-stage pipeline alternates between eliminating possible incorrect labels and semi-supervised training. However, discarding part of noisy labels could…

This work proposes a new image analysis tool called Label Consistent Transform Learning (LCTL). Transform learning is a recent unsupervised representation learning approach; we add supervision by incorporating a label consistency…

This paper concerns the use of objectness measures to improve the calibration performance of Convolutional Neural Networks (CNNs). CNNs have proven to be very good classifiers and generally localize objects well; however, the loss functions…

Mixup style data augmentation algorithms have been widely adopted in various tasks as implicit network regularization on representation learning to improve model generalization, which can be achieved by a linear interpolation of labeled…

The objective of machine unlearning (MU) is to eliminate previously learned data from a model. However, it is challenging to strike a balance between computation cost and performance when using existing MU techniques. Taking inspiration…

Images suffer from heavy spatial redundancy because pixels in neighboring regions are spatially correlated. Existing approaches strive to overcome this limitation by reducing less meaningful image regions. However, current leading methods…