Related papers: CP2: Copy-Paste Contrastive Pretraining for Semant…
Instance-level contrastive learning techniques, which rely on data augmentation and a contrastive loss function, have found great success in the domain of visual representation learning. They are not suitable for exploiting the rich…
Contrastive self-supervised learning has attracted significant research attention recently. It learns effective visual representations from unlabeled data by embedding augmented views of the same image close to each other while pushing away…
The Image Difference Captioning (IDC) task aims to describe the visual differences between two similar images with natural language. The major challenges of this task lie in two aspects: 1) fine-grained visual differences that require…
This paper proposes a scalable and straightforward pre-training paradigm for efficient visual conceptual representation called occluded image contrastive learning (OCL). Our OCL approach is simple: we randomly mask patches to generate…
Pursuing realistic results according to human visual perception is the central concern in the image transformation tasks. Perceptual learning approaches like perceptual loss are empirically powerful for such tasks but they usually rely on…
Generating accurate and coherent image captions in a continual learning setting remains a major challenge due to catastrophic forgetting and the difficulty of aligning evolving visual concepts with language over time. In this work, we…
Recently, semantic communication has been widely applied in wireless image transmission systems as it can prioritize the preservation of meaningful semantic information in images over the accuracy of transmitted symbols, leading to improved…
Labeling videos at scale is impractical. Consequently, self-supervised visual representation learning is key for efficient video analysis. Recent success in learning image representations suggests contrastive learning is a promising…
State-of-the-art semantic image segmentation methods are mostly based on training deep convolutional neural networks (CNNs). In this work, we proffer to improve semantic segmentation with the use of contextual information. In particular, we…
A key challenge in training neural networks for a given medical imaging task is often the difficulty of obtaining a sufficient number of manually labeled examples. In contrast, textual imaging reports, which are often readily available in…
Training a Fully Convolutional Network (FCN) for semantic segmentation requires a large number of masks with pixel level labelling, which involves a large amount of human labour and time for annotation. In contrast, web images and their…
Semi-supervised learning has demonstrated great potential in medical image segmentation by utilizing knowledge from unlabeled data. However, most existing approaches do not explicitly capture high-level semantic relations between distant…
Contrastive learning has been adopted as a core method for unsupervised visual representation learning. Without human annotation, the common practice is to perform an instance discrimination task: Given a query image crop, this task labels…
Semi-Supervised Semantic Segmentation (S4) aims to train a segmentation model with limited labeled images and a substantial volume of unlabeled images. To improve the robustness of representations, powerful methods introduce a pixel-wise…
Deep learning architectures exhibit a critical drop of performance due to catastrophic forgetting when they are required to incrementally learn new tasks. Contemporary incremental learning frameworks focus on image classification and object…
Asymmetric appearance between positive pair effectively reduces the risk of representation degradation in contrastive learning. However, there are still a mass of appearance similarities between positive pair constructed by the existing…
Semantic segmentation has made tremendous progress in recent years. However, satisfying performance highly depends on a large number of pixel-level annotations. Therefore, in this paper, we focus on the semi-supervised segmentation problem…
Despite great improvements in semantic segmentation, challenges persist because of the lack of local/global contexts and the relationship between them. In this paper, we propose Contextrast, a contrastive learning-based semantic…
In seismic interpretation, pixel-level labels of various rock structures can be time-consuming and expensive to obtain. As a result, there oftentimes exists a non-trivial quantity of unlabeled data that is left unused simply because…
Contrastive learning has achieved remarkable success on various high-level tasks, but there are fewer contrastive learning-based methods proposed for low-level tasks. It is challenging to adopt vanilla contrastive learning technologies…