Related papers: Dense Semantic Contrast for Self-Supervised Visual…

The key to integrating visual language tasks is to establish a good alignment strategy. Recently, visual semantic representation has achieved fine-grained visual understanding by dividing grids or image patches. However, the coarse-grained…

Contrastive learning methods for unsupervised visual representation learning have reached remarkable levels of transfer performance. We argue that the power of contrastive learning has yet to be fully unleashed, as current methods are…

Recently, dense contrastive learning has shown superior performance on dense prediction tasks compared to instance-level contrastive learning. Despite its supremacy, the properties of dense contrastive representations have not yet been…

Contemporary transfer learning-based methods to alleviate the data insufficiency in change detection (CD) are mainly based on ImageNet pre-training. Self-supervised learning (SSL) has recently been introduced to remote sensing (RS) for…

Recently, contrastive learning has largely advanced the progress of unsupervised visual representation learning. Pre-trained on ImageNet, some self-supervised algorithms reported higher transfer learning performance compared to…

Deep clustering against self-supervised learning is a very important and promising direction for unsupervised visual representation learning since it requires little domain knowledge to design pretext tasks. However, the key component,…

Although there is significant progress in supervised semantic segmentation, it remains challenging to deploy the segmentation models to unseen domains due to domain biases. Domain adaptation can help in this regard by transferring knowledge…

Generalized Zero-Shot Learning (GZSL) targets recognizing new categories by learning transferable image representations. Existing methods find that, by aligning image representations with corresponding semantic labels, the semantic-aligned…

Self-supervised 3D representation learning aims to learn effective representations from large-scale unlabeled point clouds. Most existing approaches adopt point discrimination as the pretext task, which assigns matched points in two…

Collecting labeled data for the task of semantic segmentation is expensive and time-consuming, as it requires dense pixel-level annotations. While recent Convolutional Neural Network (CNN) based semantic segmentation approaches have…

In recent years Convolutional neural networks (CNN) have made significant progress in computer vision. These advancements have been applied to other areas, such as remote sensing and have shown satisfactory results. However, the lack of…

Recently, self-supervised methods show remarkable achievements in image-level representation learning. Nevertheless, their image-level self-supervisions lead the learned representation to sub-optimal for dense prediction tasks, such as…

Semantic image parsing, which refers to the process of decomposing images into semantic regions and constructing the structure representation of the input, has recently aroused widespread interest in the field of computer vision. The recent…

Weakly supervised semantic segmentation (WSSS) aims at learning a semantic segmentation model with only image-level tags. Despite intensive research on deep learning approaches over a decade, there is still a significant performance gap…

To extract robust deep representations from long sequential modeling of speech data, we propose a self-supervised learning approach, namely Contrastive Separative Coding (CSC). Our key finding is to learn such representations by separating…

In recent years self-supervised learning has emerged as a promising candidate for unsupervised representation learning. In the visual domain its applications are mostly studied in the context of images of natural scenes. However, its…

In this work, we present Multi-Level Contrastive Learning for Dense Prediction Task (MCL), an efficient self-supervised method for learning region-level feature representation for dense prediction tasks. Our method is motivated by the three…

Hierarchical semantic structures naturally exist in an image dataset, in which several semantically relevant image clusters can be further integrated into a larger cluster with coarser-grained semantics. Capturing such structures with image…

Unsupervised semantic segmentation requires assigning a label to every pixel without any human annotations. Despite recent advances in self-supervised representation learning for individual images, unsupervised semantic segmentation with…

Recently, significant advancements in artificial intelligence have been attributed to the integration of self-supervised learning (SSL) scheme. While SSL has shown impressive achievements in natural language processing (NLP), its progress…