Multi-modal foundation models such as CLIP have showcased impressive zero-shot
capabilities. However, their applicability in resource-constrained environments is limited due …

This report presents the ECO (Ensembled Clip score and cOnsensus score) pipeline from
team DSBA LAB which is a new framework used to evaluate and rank captions for a given …

Generative text-to-image models enable us to synthesize unlimited amounts of images in a
controllable manner, spurring many recent efforts to train vision models with synthetic data …

Vision and language models (VLMs) such as CLIP have showcased remarkable zero-shot
recognition abilities yet face challenges in visio-linguistic compositionality, particularly in …

Generative retrieval, which has demonstrated effectiveness in text-to-text retrieval, utilizes a
sequence-to-sequence model to directly generate candidate identifiers based on natural …

This work presents a tuning-free semantic segmentation framework based on classifying
SAM masks by CLIP, which is universally applicable to various types of supervision. Initially …

CLIP models perform remarkably well on zero-shot classification and retrieval tasks. But
recent studies have shown that learnt representations in CLIP are not well suited for dense …

Humans describe complex scenes with compositionality, using simple text descriptions
enriched with links and relationships. While vision-language research has aimed to develop …

Contrastive learning has gained widespread adoption for retrieval tasks due to its minimal
requirement for manual annotations. However, popular contrastive frameworks typically …

Vision Foundation Models (VFMs) pretrained on massive datasets exhibit impressive
performance on various downstream tasks, especially with limited labeled target data …