Facial emotion recognition (FER) is significant for human-computer interaction such as
clinical practice and behavioral description. Accurate and robust FER by computer models …

Neural architecture search (NAS) has attracted increasing attention. In recent years,
individual search methods have been replaced by weight-sharing search methods for higher …

Diffusion models currently dominate the field of data-driven image synthesis with their
unparalleled scaling to large datasets. In this paper we identify and rectify several causes for …

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 …

Transfer of pre-trained representations improves sample efficiency and simplifies
hyperparameter tuning when training deep neural networks for vision. We revisit the …

Scaling up the convolutional neural network (CNN) size (eg, width, depth, etc.) is known to
effectively improve model accuracy. However, the large model size impedes training on …

In facial expression recognition (FER), the uncertainties introduced by inherent noises like
ambiguous facial expressions and inconsistent labels raise concerns about the credibility of …

We study whether a neural network optimizes to the same, linearly connected minimum
under different samples of SGD noise (eg, random data order and augmentation). We find …

We empirically demonstrate that full-batch gradient descent on neural network training
objectives typically operates in a regime we call the Edge of Stability. In this regime, the …

Abstract Normalization layers (eg, Batch Normalization, Layer Normalization) were
introduced to help with optimization difficulties in very deep nets, but they clearly also help …