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 …

Multimodal deep learning systems that employ multiple modalities like text, image, audio,
video, etc., are showing better performance than individual modalities (ie, unimodal) …

Recent large-scale generative models learned on big data are capable of synthesizing
incredible images yet suffer from limited controllability. This work offers a new generation …

Federated learning has emerged as an important distributed learning paradigm, which
normally involves collaborative updating with others and local updating on private data …

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 …

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 …

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 …

Most existing datasets for sound event recognition (SER) are relatively small and/or domain-
specific, with the exception of AudioSet, based on over 2 M tracks from YouTube videos and …

Deep neural networks are known to be annotation-hungry. Numerous efforts have been
devoted to reducing the annotation cost when learning with deep networks. Two prominent …