To ensure good performance, modern machine learning models typically require large
amounts of quality annotated data. Meanwhile, the data collection and annotation processes …

Deep learning has achieved remarkable results in many computer vision tasks. Deep neural
networks typically rely on large amounts of training data to avoid overfitting. However …

Automatic augmentation methods have recently become a crucial pillar for strong model
performance in vision tasks. While existing automatic augmentation methods need to trade …

Deep learning (DL) has become one of the mainstream and effective methods for point
cloud analysis tasks such as detection, segmentation and classification. To reduce …

Optimization of image transformation functions for the purpose of data augmentation has
been intensively studied. In particular, adversarial data augmentation strategies, which …

The superior performance of modern deep networks usually comes with a costly training
procedure. This paper presents a new curriculum learning approach for the efficient training …

Person re-identification is a hot topic in computer vision, and the loss function plays a vital
role in improving the discrimination of the learned features. However, most existing models …

Data augmentation has been an indispensable tool to improve the performance of deep
neural networks, however the augmentation can hardly transfer among different tasks and …

The goal of image harmonization is adjusting the foreground appearance in a composite
image to make the whole image harmonious. To construct paired training images, existing …

Data augmentation is an effective way to improve the generalization of deep learning
models. However, the underlying augmentation methods mainly rely on handcrafted …