Deep supervised learning algorithms typically require a large volume of labeled data to
achieve satisfactory performance. However, the process of collecting and labeling such data …

Deep learning has achieved great success in learning features from massive remote
sensing images (RSIs). To better understand the connection between three feature learning …

Self-supervised learning (SSL) has achieved remarkable performance in various medical
imaging tasks by dint of priors from massive unlabeled data. However, regarding a specific …

Abstract The task of Human-Object Interaction (HOI) detection targets fine-grained visual
parsing of humans interacting with their environment, enabling a broad range of …

Abstract Few-Shot Class-Incremental Learning (FSCIL) introduces a paradigm in which the
problem space expands with limited data. FSCIL methods inherently face the challenge of …

Annotating images with pixel-wise labels is a time-consuming and costly process. Recently,
DatasetGAN showcased a promising alternative-to synthesize a large labeled dataset via a …

Empowered by large datasets, eg, ImageNet and MS COCO, unsupervised learning on
large-scale data has enabled significant advances for classification tasks. However, whether …

In computer vision, fine-tuning is the de-facto approach to leverage pre-trained vision
models to perform downstream tasks. However, deploying it in practice is quite challenging …

An ideal learned representation should display transferability and robustness. Supervised
contrastive learning (SupCon) is a promising method for training accurate models, but …

The pretrain-finetune paradigm is a classical pipeline in visual learning. Recent progress on
unsupervised pretraining methods shows superior transfer performance to their supervised …