Vision-language models (VLMs) are typically composed of a vision encoder, eg CLIP, and a
language model (LM) that interprets the encoded features to solve downstream tasks …

As the most fundamental scene understanding tasks, object detection and segmentation
have made tremendous progress in deep learning era. Due to the expensive manual …

Open-vocabulary semantic segmentation requires models to effectively integrate visual
representations with open-vocabulary semantic labels. While Contrastive Language-Image …

We introduce eCLIP, an enhanced version of the CLIP model that integrates expert
annotations in the form of radiologist eye-gaze heatmaps. It tackles key challenges in …

In semi-supervised semantic segmentation, a model is trained with a limited number of
labeled images along with a large corpus of unlabeled images to reduce the high annotation …

Contrastive Language-Image Pre-training (CLIP) has been a celebrated method for training
vision encoders to generate image/text representations facilitating various applications …

Image segmentation is a long-standing challenge in computer vision, studied continuously
over several decades, as evidenced by seminal algorithms such as N-Cut, FCN, and …

Vision-Language Models (VLMs) trained via contrastive learning have achieved notable
success in natural image tasks. However, their application in the medical domain remains …

Knowledge distillation (KD) is the de facto standard for compressing large-scale models into
smaller ones. Prior works have explored ever more complex KD strategies involving different …

We present a novel LLM-based pipeline for creating contextual descriptions of human body
poses in images using only auxiliary attributes. This approach facilitates the creation of the …