Mixup is a well-known data-dependent augmentation technique for DNNs, consisting of two
sub-tasks: mixup generation and classification. However, the recent dominant online training …

With the remarkable progress of deep neural networks in computer vision, data mixing
augmentation techniques are widely studied to alleviate problems of degraded …

The downstream accuracy of self-supervised methods is tightly linked to the proxy task
solved during training and the quality of the gradients extracted from it. Richer and more …

Cluster discrimination is an effective pretext task for unsupervised representation learning,
which often consists of two phases: clustering and discrimination. Clustering is to assign …

In computer vision, pre-training models based on large-scale supervised learning have
been proven effective over the past few years. However, existing works mostly focus on …

The superiority of deeply learned representations relies on large-scale labeled datasets.
However, annotating data are usually expensive or even infeasible in some scenarios. To …

Data mixing augmentation have proved to be effective for improving the generalization
ability of deep neural networks. While early methods mix samples by hand-crafted policies …

Unsupervised representation learning with contrastive learning achieves great success
recently. However, these methods have to duplicate each training batch to construct …

Self-supervised learning aims to learn representations from the data itself without explicit
manual supervision. Existing efforts ignore a crucial aspect of self-supervised learning-the …

Visual Prompt Tuning (VPT) techniques have gained prominence for their capacity to adapt
pre-trained Vision Transformers (ViTs) to downstream visual tasks using specialized …