Albeit the notable performance on in-domain test points, it is non-trivial for deep neural
networks to attain satisfactory accuracy when deploying in the open world, where novel …

Convolutional Neural Networks (CNNs) have brought revolutionary advances to many
research areas due to their capacity of learning from raw data. However, when those …

Open-Set Domain Adaptation (OSDA) aims at adapting a model trained on a labelled source
domain, to an unlabeled target domain that is corrupted with unknown classes. The key …

Convolutional neural networks (CNNs) can learn directly from raw data, resulting in
exceptional performance across various research areas. However, factors present in non …

Convolutional neural networks (CNNs) can learn directly from raw data, resulting in
exceptional performance across various research areas. However, factors present in non …

Natural image matting is the task of precisely estimating alpha mattes to separate
foreground objects from background images. Existing matting methods only focus on …

Convolutional Neural Networks (CNNs) have brought revolutionary advances to many
research areas due to their capacity of learning from raw data. However, when those …

In these days the world is wondering about the potentialities and risks of artificial intelligence
models trained on a huge amount of data and computational resources. While this debate is …

Abstract Domain generalization (DG) for image classification is a crucial task in machine
learning that focuses on transferring domain-invariant knowledge from multiple source …

Deep learning (DL) has revolutionized various fields through its remarkable capacity to learn
from raw data. However, in uncontrolled environments like in the wild, the performance of …