Related papers: Disentangling Sampling and Labeling Bias for Learn…

Deep neural networks trained with standard cross-entropy loss are more prone to memorize noisy labels, which degrades their performance. Negative learning using complementary labels is more robust when noisy labels intervene but with an…

A prominent technique for self-supervised representation learning has been to contrast semantically similar and dissimilar pairs of samples. Without access to labels, dissimilar (negative) points are typically taken to be randomly sampled…

Given data with label noise (i.e., incorrect data), deep neural networks would gradually memorize the label noise and impair model performance. To relieve this issue, curriculum learning is proposed to improve model performance and…

Multi-label classification is a widely encountered problem in daily life, where an instance can be associated with multiple classes. In theory, this is a supervised learning method that requires a large amount of labeling. However,…

Negative sampling has emerged as an effective technique that enables deep learning models to learn better representations by introducing the paradigm of learn-to-compare. The goal of this approach is to add robustness to deep learning…

In semantic segmentation, training data down-sampling is commonly performed due to limited resources, the need to adapt image size to the model input, or improve data augmentation. This down-sampling typically employs different strategies…

Motivated by applications in protein function prediction, we consider a challenging supervised classification setting in which positive labels are scarce and there are no explicit negative labels. The learning algorithm must thus select…

The aim of Active Learning is to select the most informative samples from an unlabelled set of data. This is useful in cases where the amount of data is large and labelling is expensive, such as in machine vision or medical imaging. Two…

Real-world data often exhibits long-tailed distributions with heavy class imbalance, posing great challenges for deep recognition models. We identify a persisting dilemma on the value of labels in the context of imbalanced learning: on the…

Fine-grained classification involves dealing with datasets with larger number of classes with subtle differences between them. Guiding the model to focus on differentiating dimensions between these commonly confusable classes is key to…

Deep learning algorithms can fare poorly when the training dataset suffers from heavy class-imbalance but the testing criterion requires good generalization on less frequent classes. We design two novel methods to improve performance in…

In many real-world pattern recognition scenarios, such as in medical applications, the corresponding classification tasks can be of an imbalanced nature. In the current study, we focus on binary, imbalanced classification tasks, i.e.~binary…

Trained classification models can unintentionally lead to biased representations and predictions, which can reinforce societal preconceptions and stereotypes. Existing debiasing methods for classification models, such as adversarial…

Deep neural networks usually perform poorly when the training dataset suffers from extreme class imbalance. Recent studies found that directly training with out-of-distribution data (i.e., open-set samples) in a semi-supervised manner would…

Negative sampling approaches are prevalent in implicit collaborative filtering for obtaining negative labels from massive unlabeled data. As two major concerns in negative sampling, efficiency and effectiveness are still not fully achieved…

In multi-label learning, leveraging contrastive learning to learn better representations faces a key challenge: selecting positive and negative samples and effectively utilizing label information. Previous studies selected positive and…

We consider the problem of retrieving the most relevant labels for a given input when the size of the output space is very large. Retrieval methods are modeled as set-valued classifiers which output a small set of classes for each input,…

The learning from imbalanced data is a deeply studied problem in standard classification and, in recent times, also in multilabel classification. A handful of multilabel resampling methods have been proposed in late years, aiming to balance…

In multi-label classification, an instance may be associated with a set of labels simultaneously. Recently, the research on multi-label classification has largely shifted its focus to the other end of the spectrum where the number of labels…

Neural networks trained on real-world datasets with long-tailed label distributions are biased towards frequent classes and perform poorly on infrequent classes. The imbalance in the ratio of positive and negative samples for each class…