Related papers: Expertise-based Weighting for Regression Models wi…

We consider training decision trees using noisily labeled data, focusing on loss functions that can lead to robust learning algorithms. Our contributions are threefold. First, we offer novel theoretical insights on the robustness of many…

Deep learning with noisy labels presents significant challenges. In this work, we theoretically characterize the role of label noise from a feature learning perspective. Specifically, we consider a signal-noise data distribution, where each…

Class imbalance and noisy labels are the norm rather than the exception in many large-scale classification datasets. Nevertheless, most works in machine learning typically assume balanced and clean data. There have been some recent attempts…

Deep Metric Learning (DML) plays a critical role in various machine learning tasks. However, most existing deep metric learning methods with binary similarity are sensitive to noisy labels, which are widely present in real-world data. Since…

Improperly constructed datasets can result in inaccurate inferences. For instance, models trained on biased datasets perform poorly in terms of generalization (i.e., dataset bias). Recent debiasing techniques have successfully achieved…

To discover intrinsic inter-class transition probabilities underlying data, learning with noise transition has become an important approach for robust deep learning on corrupted labels. Prior methods attempt to achieve such transition…

We present a theoretically grounded approach to train deep neural networks, including recurrent networks, subject to class-dependent label noise. We propose two procedures for loss correction that are agnostic to both application domain and…

We present a practical and statistically consistent scheme for actively learning binary classifiers under general loss functions. Our algorithm uses importance weighting to correct sampling bias, and by controlling the variance, we are able…

An accurate and substantial dataset is essential for training a reliable and well-performing model. However, even manually annotated datasets contain label errors, not to mention automatically labeled ones. Previous methods for label…

As with many other problems, real-world regression is plagued by the presence of noisy labels, an inevitable issue that demands our attention. Fortunately, much real-world data often exhibits an intrinsic property of continuously ordered…

Risk assessment tools are widely used around the country to inform decision making within the criminal justice system. Recently, considerable attention has been devoted to the question of whether such tools may suffer from racial bias. In…

Deep neural networks tend to memorize noisy labels, severely degrading their generalization performance. Although Mixup has demonstrated effectiveness in improving generalization and robustness, existing Mixup-based methods typically…

With the explosion of massive, widely available unlabeled data in the past years, finding label and time efficient, robust learning algorithms has become ever more important in theory and in practice. We study the paradigm of active…

Real-world large-scale datasets are both noisily labeled and class-imbalanced. The issues seriously hurt the generalization of trained models. It is hence significant to address the simultaneous incorrect labeling and class-imbalance, i.e.,…

ConvNets achieve good results when training from clean data, but learning from noisy labels significantly degrades performances and remains challenging. Unlike previous works constrained by many conditions, making them infeasible to real…

In the surface defect detection, there are some suspicious regions that cannot be uniquely classified as abnormal or normal. The annotating of suspicious regions is easily affected by factors such as workers' emotional fluctuations and…

Labeling data correctly is an expensive and challenging task in machine learning, especially for on-line data streams. Deep learning models especially require a large number of clean labeled data that is very difficult to acquire in…

Recently, variational autoencoders have been successfully used to learn a probabilistic prior over speech signals, which is then used to perform speech enhancement. However, variational autoencoders are trained on clean speech only, which…

Interactive learning is a process in which a machine learning algorithm is provided with meaningful, well-chosen examples as opposed to randomly chosen examples typical in standard supervised learning. In this paper, we propose a new method…

State-of-the-art object detectors rely on regressing and classifying an extensive list of possible anchors, which are divided into positive and negative samples based on their intersection-over-union (IoU) with corresponding groundtruth…