The prosperity of machine learning has been accompanied by increasing attacks on the
training process. Among them, poisoning attacks have become an emerging threat during …

Deep learning has achieved remarkable success in numerous domains with help from large
amounts of big data. However, the quality of data labels is a concern because of the lack of …

Unsupervised person re-identification (re-ID) aims at learning discriminative representations
for person retrieval from unlabeled data. Recent techniques accomplish this task by using …

Deep networks have strong capacities of embedding data into latent representations and
finishing following tasks. However, the capacities largely come from high-quality annotated …

We identify label errors in the test sets of 10 of the most commonly-used computer vision,
natural language, and audio datasets, and subsequently study the potential for these label …

Data-centric AI is at the center of a fundamental shift in software engineering where machine
learning becomes the new software, powered by big data and computing infrastructure …

Abstract Noisy label Facial Expression Recognition (FER) is more challenging than
traditional noisy label classification tasks due to the inter-class similarity and the annotation …

Supervised deep learning methods require a large repository of annotated data; hence,
label noise is inevitable. Training with such noisy data negatively impacts the generalization …

Abstract Model heterogeneous federated learning is a challenging task since each client
independently designs its own model. Due to the annotation difficulty and free-riding …

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 …