Related papers: Probing Intrinsic Medical Task Relationships: A Co…

Humans commonly work with multiple objects in daily life and can intuitively transfer manipulation skills to novel objects by understanding object functional regularities. However, existing technical approaches for analyzing and…

Contrastive learning between different views of the data achieves outstanding success in the field of self-supervised representation learning and the learned representations are useful in broad downstream tasks. Since all supervision…

Semantic segmentation of outdoor scenes is problematic when there are variations in imaging conditions. It is known that albedo (reflectance) is invariant to all kinds of illumination effects. Thus, using reflectance images for semantic…

Self-supervised methods have shown tremendous success in the field of computer vision, including applications in remote sensing and medical imaging. Most popular contrastive-loss based methods like SimCLR, MoCo, MoCo-v2 use multiple views…

Medical image interpretation using deep learning has shown promise but often requires extensive expert-annotated datasets. To reduce this annotation burden, we develop an Image-Graph Contrastive Learning framework that pairs chest X-rays…

Self-supervised pre-training of deep learning models with contrastive learning is a widely used technique in image analysis. Current findings indicate a strong potential for contrastive pre-training on medical images. However, further…

Multiview network embedding aims at projecting nodes in the network to low-dimensional vectors, while preserving their multiple relations and attribute information. Contrastive learning approaches have shown promising performance in this…

Much of vision-and-language research focuses on a small but diverse set of independent tasks and supporting datasets often studied in isolation; however, the visually-grounded language understanding skills required for success at these…

Learning robust representations to discriminate cell phenotypes based on microscopy images is important for drug discovery. Drug development efforts typically analyse thousands of cell images to screen for potential treatments. Early works…

Unsupervised region representation learning aims to extract dense and effective features from unlabeled urban data. While some efforts have been made for solving this problem based on multiple views, existing methods are still insufficient…

Vision and touch are two fundamental sensory modalities for robots, offering complementary information that enhances perception and manipulation tasks. Previous research has attempted to jointly learn visual-tactile representations to…

Integrating computation into physics teaching is a curricular move that, at present, has been predominately studied for its cognitive impacts. However, if this modality of instruction shifts how students engage with physics, we argue there…

Modern vision models have achieved strong object-recognition performance, yet it remains unclear whether their representations encode object-level semantic relatedness, the meaningful connection between object concepts that supports human…

Recently, contrastive learning-based image translation methods have been proposed, which contrasts different spatial locations to enhance the spatial correspondence. However, the methods often ignore the diverse semantic relation within the…

In human neuroscience, machine learning can help reveal lower-dimensional neural representations relevant to subjects' behavior. However, state-of-the-art models typically require large datasets to train, so are prone to overfitting on…

Medical report generation is a challenging task since it is time-consuming and requires expertise from experienced radiologists. The goal of medical report generation is to accurately capture and describe the image findings. Previous works…

The application of self-supervised techniques has become increasingly prevalent within medical visualization tasks, primarily due to its capacity to mitigate the data scarcity prevalent in the healthcare sector. The majority of current…

In this study, we address the intricate challenge of multi-task dense prediction, encompassing tasks such as semantic segmentation, depth estimation, and surface normal estimation, particularly when dealing with partially annotated data…

Models for image representation learning are typically designed for either recognition or generation. Various forms of contrastive learning help models learn to convert images to embeddings that are useful for classification, detection, and…

We define the concept of CompositeTasking as the fusion of multiple, spatially distributed tasks, for various aspects of image understanding. Learning to perform spatially distributed tasks is motivated by the frequent availability of only…