Artificial Intelligence (AI) is making a profound impact in almost every domain. A vital enabler
of its great success is the availability of abundant and high-quality data for building machine …

The existing weakly supervised semantic segmentation (WSSS) methods pay much
attention to generating accurate and complete class activation maps (CAMs) as pseudo …

The sample selection approach is popular in learning with noisy labels. The state-of-the-art
methods train two deep networks simultaneously for sample selection, which aims to employ …

Noisy labels are unavoidable yet troublesome in the ecosystem of deep learning because
models can easily overfit them. There are many types of label noise, such as symmetric …

The rawly collected training data often comes with separate noisy labels collected from
multiple imperfect annotators (eg, via crowdsourcing). A typical way of using these separate …

Learning from crowds describes that the annotations of training data are obtained with
crowd-sourcing services. Multiple annotators each complete their own small part of the …

Learning from multiple annotators aims to induce a high-quality classifier from training
instances, where each of them is associated with a set of observed labels provided by …

Designing robust loss functions is popular in learning with noisy labels while existing
designs did not explicitly consider the overfitting property of deep neural networks (DNNs) …

Label errors have been found to be prevalent in popular text, vision, and audio datasets,
which heavily influence the safe development and evaluation of machine learning …

Federated Learning (FL) heavily depends on label quality for its performance. However, the
label distribution among individual clients is always both noisy and heterogeneous. The …