Related papers: Learning under noisy supervision is governed by a …

Recent advances in deep learning have relied on large, labelled datasets to train high-capacity models. However, collecting large datasets in a time- and cost-efficient manner often results in label noise. We present a method for learning…

We reformulate the problem of supervised learning as learning to learn with two nested loops (i.e. learning problems). The inner loop learns on each individual instance with self-supervision before final prediction. The outer loop learns…

We propose a novel framework to perform classification via deep learning in the presence of noisy annotations. When trained on noisy labels, deep neural networks have been observed to first fit the training data with clean labels during an…

Continually learning in the real world must overcome many challenges, among which noisy labels are a common and inevitable issue. In this work, we present a repla-ybased continual learning framework that simultaneously addresses both…

This paper introduces an interactive continual learning paradigm where AI models dynamically learn new skills from real-time human feedback while retaining prior knowledge. This paradigm distinctively addresses two major limitations of…

In this paper, we investigate the problem of learning with noisy labels in real-world annotation scenarios, where noise can be categorized into two types: factual noise and ambiguity noise. To better distinguish these noise types and…

Deep neural network can easily overfit to even noisy labels due to its high capacity, which degrades the generalization performance of a model. To overcome this issue, we propose a new approach for learning from noisy labels (LNL) via…

Highly over-parameterized models can simultaneously memorize noisy labels and generalize well, yet how these behaviors coexist remains poorly understood. In this work, we investigate the underlying mechanisms of this coexistence using…

The performance of a model trained with noisy labels is often improved by simply \textit{retraining} the model with its \textit{own predicted hard labels} (i.e., 1/0 labels). Yet, a detailed theoretical characterization of this phenomenon…

Training deep neural networks (DNNs) with noisy labels is a challenging problem due to over-parameterization. DNNs tend to essentially fit on clean samples at a higher rate in the initial stages, and later fit on the noisy samples at a…

With the widespread use of machine learning for classification, it becomes increasingly important to be able to use weaker kinds of supervision for tasks in which it is hard to obtain standard labeled data. One such kind of supervision is…

In many applications, training machine learning models involves using large amounts of human-annotated data. Obtaining precise labels for the data is expensive. Instead, training with weak supervision provides a low-cost alternative. We…

The ability of a brain or a neural network to efficiently learn depends crucially on both the task structure and the learning rule. Previous works have analyzed the dynamical equations describing learning in the relatively simplified…

Advances in neural modeling have achieved state-of-the-art (SOTA) results on public natural language processing (NLP) benchmarks, at times surpassing human performance. However, there is a gap between public benchmarks and real-world…

How deep neural networks (DNNs) learn from noisy labels has been studied extensively in image classification but much less in image segmentation. So far, our understanding of the learning behavior of DNNs trained by noisy segmentation…

Learning with noisy labels has attracted a lot of attention in recent years, where the mainstream approaches are in pointwise manners. Meanwhile, pairwise manners have shown great potential in supervised metric learning and unsupervised…

Deep neural networks have been shown to be very powerful methods for many supervised learning tasks. However, they can also easily overfit to training set biases, i.e., label noise and class imbalance. While both learning with noisy labels…

We propose self-adaptive training -- a unified training algorithm that dynamically calibrates and enhances training processes by model predictions without incurring an extra computational cost -- to advance both supervised and…

Recent progress in singing voice separation has primarily focused on supervised deep learning methods. However, the scarcity of ground-truth data with clean musical sources has been a problem for long. Given a limited set of labeled data,…

Labor-intensive labeling becomes a bottleneck in developing computer vision algorithms based on deep learning. For this reason, dealing with imperfect labels has increasingly gained attention and has become an active field of study. We…