Self-supervised learning (SSL) is a potential deep learning (DL) technique that uses
massive volumes of unlabeled data to train neural networks. SSL techniques have evolved …

Progress in self-supervised learning has brought strong general image representation
learning methods. Yet so far, it has mostly focused on image-level learning. In turn, tasks …

Learning inter-image similarity is crucial for 3D medical images self-supervised pre-training,
due to their sharing of numerous same semantic regions. However, the lack of the semantic …

We present a collaborative learning method called Mutual Contrastive Learning (MCL) for
general visual representation learning. The core idea of MCL is to perform mutual interaction …

In real applications, new object classes often emerge after the detection model has been
trained on a prepared dataset with fixed classes. Fine-tuning the old model with only new …

Unsupervised semantic segmentation aims to obtain high-level semantic representation on
low-level visual features without manual annotations. Most existing methods are bottom-up …

We propose a latent diffusion model with contrastive learning for audio-visual segmentation
(AVS) to extensively explore the contribution of audio. We interpret AVS as a conditional …

Visual text, a pivotal element in both document and scene images, speaks volumes and
attracts significant attention in the computer vision domain. Beyond visual text detection and …

Unsupervised object discovery (UOD) refers to the task of discriminating the whole region of
objects from the background within a scene without relying on labeled datasets, which …

Ambiguous scene text detection is an extremely challenging task. Existing text detectors that
rely solely on visual cues often suffer from confusion due to being evenly distributed in …