Related papers: Topological Alignment of Shared Vision-Language Em…

Most existing semantic communication (SemCom) systems use deep joint source-channel coding (DeepJSCC) to encode task-specific semantics in a goal-oriented manner. However, their reliance on predefined tasks and datasets significantly limits…

Safe autonomous systems in complex environments require robust road anomaly segmentation to identify unknown obstacles. However, existing approaches often rely on pixel-level statistics to determine whether a region appears anomalous. This…

Recent advances in vision-language models (VLMs) have demonstrated remarkable zero-shot capabilities, yet adapting these models to specialized domains remains a significant challenge. Building on recent theoretical insights suggesting that…

This letter proposes a method of global localization on a map with semantic object landmarks. One of the most promising approaches for localization on object maps is to use semantic graph matching using landmark descriptors calculated from…

Concept Bottleneck Models (CBM) map images to human-interpretable concepts before making class predictions. Recent approaches automate CBM construction by prompting Large Language Models (LLMs) to generate text concepts and employing Vision…

Contrastive Language-Image Pretraining (CLIP) performs zero-shot image classification by mapping images and textual class representation into a shared embedding space, then retrieving the class closest to the image. This work provides a new…

Existing vision-text contrastive learning models enhance representation transferability and support zero-shot prediction by matching paired image and caption embeddings while pushing unrelated pairs apart. However, astronomical image-label…

We present a unified vision-language framework tailored for ENT endoscopy image analysis that simultaneously tackles three clinically-relevant tasks: image classification, image-to-image retrieval, and text-to-image retrieval. Unlike…

Topological correctness is critical for segmentation of tubular structures, which pervade in biomedical images. Existing topological segmentation loss functions are primarily based on the persistent homology of the image. They match the…

Vision-language models (VLMs) exhibit affirmation bias: a systematic tendency to select positive captions ("X is present") even when the correct description contains negation ("no X"). While prior work has documented this failure mode in…

Vision-language models (VLMs), such as CLIP and SigLIP, have found remarkable success in classification, retrieval, and generative tasks. For this, VLMs deterministically map images and text descriptions to a joint latent space in which…

Large Language Models (LLMs) have demonstrated strong capabilities in natural language understanding and reasoning, while recent extensions that incorporate visual inputs enable them to process multimodal information. Despite these…

Large-scale pre-trained Vision-Language Models (VLMs) have become essential for transfer learning across diverse tasks. However, adapting these models with limited few-shot data often leads to overfitting, diminishing their performance on…

Modeling medical vessel-like anatomy is challenging due to its intricate topology and sensitivity to dataset shifts. Consequently, task-specific models often suffer from topological inconsistencies, including artificial disconnections and…

Contrastive pre-training on image-text pairs, exemplified by CLIP, becomes a standard technique for learning multi-modal visual-language representations. Although CLIP has demonstrated remarkable performance, training it from scratch on…

CLIP (Contrastive Language-Image Pre-training) uses contrastive learning from noise image-text pairs to excel at recognizing a wide array of candidates, yet its focus on broad associations hinders the precision in distinguishing subtle…

Pre-trained Vision-Language Models (VLMs), such as CLIP, have shown enhanced performance across a range of tasks that involve the integration of visual and linguistic modalities. When CLIP is used for depth estimation tasks, the patches,…

Image Captioning for state-of-the-art VLMs has significantly improved over time; however, this comes at the cost of increased computational complexity, making them less accessible for resource-constrained applications such as mobile devices…

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

This paper describes our zero-shot approaches for the Visual Word Sense Disambiguation (VWSD) Task in English. Our preliminary study shows that the simple approach of matching candidate images with the phrase using CLIP suffers from the…