Sharpness-aware minimization (SAM) was proposed to reduce sharpness of minima and
has been shown to enhance generalization performance in various settings. In this work we …

State-of-the-art deep learning systems (eg, ImageNet image classification) typically require
very large training sets to achieve high accuracies. Therefore, one of the grand challenges is …

Federated Learning (FL) is an emerging paradigm that allows a model to be trained across a
number of participants without sharing data. Recent works have begun to consider the …

Recently, a number of iterative learning methods have been introduced to improve
generalization. These typically rely on training for longer periods of time in exchange for …

Due to the covariate shift, deep neural networks performance always degrades when
applied to novel domains. In order to mitigate this problem, domain adaptation techniques …

Learning the generalizable feature representation is critical to few-shot image classification.
While recent works exploited task-specific feature embedding using meta-tasks for few-shot …

Multi-label image recognition aims to predict a set of labels that present in an image. The
key to deal with such problem is to mine the associations between image contents and …

Remote sensing object labels require high specialization, resulting in a limited number of
labeled samples. Without large labeled samples to support training, general remote sensing …

The paradigm of “pretraining-then-finetuning”(PT-FT) has been extensively explored to
enhance the performance of clinical applications with limited annotations. A major …

In this paper, we explore self-supervised learning (SSL) for analyzing a first-of-its-kind
database of cry recordings containing clinical indications of more than a thousand …