Large-scale multi-modal contrastive pre-training has demonstrated great utility to learn
transferable features for a range of downstream tasks by mapping multiple modalities into a …

Contrastive learning has proven effective for pre-training image models on unlabeled data
with promising results for tasks such as medical image classification. Using paired text (like …

Abstract Vision-Language Pre-Training (VLP) has shown promising capabilities to align
image and text pairs, facilitating a broad variety of cross-modal learning tasks. However, we …

The development of vision models for real-world applications is hindered by the challenge of
annotated data scarcity, which has necessitated the adoption of data-efficient visual learning …

Self-supervised pre-training on unlabeled images has shown promising results in the
medical domain. Recently, methods using text-supervision from companion text like …

We present Answer-Me, a task-aware multi-task framework which unifies a variety of
question answering tasks, such as, visual question answering, visual entailment, visual …

We propose FindIt, a simple and versatile framework that unifies a variety of visual
grounding and localization tasks including referring expression comprehension, text-based …

Despite the rapid advancement of unsupervised learning in visual representation, it requires
training on large-scale datasets that demand costly data collection, and pose additional …

Vision-Language Pre-Training (VLP) has demonstrated remarkable potential in aligning
image and text pairs, paving the way for a wide range of cross-modal learning tasks …

Training object detectors to segment large numbers of classes is challenging because they
require training masks for each class. A potential solution is to partially supervise detectors …