Related papers: Enhancing CLIP Robustness via Cross-Modality Align…
Pre-trained vision-language models (VLMs) such as CLIP have demonstrated strong zero-shot capabilities across diverse domains, yet remain highly vulnerable to adversarial perturbations that disrupt image-text alignment and compromise…
Vision-Language Models (VLMs) achieve strong cross-modal performance, yet recent evidence suggests they over-rely on textual descriptions while under-utilizing visual evidence -- a phenomenon termed ``text shortcut learning.'' We propose an…
Pretrained vision-language models (VLMs) like CLIP exhibit exceptional generalization across diverse downstream tasks. While recent studies reveal their vulnerability to adversarial attacks, research to date has primarily focused on…
The robustness of Vision-Language Models (VLMs) such as CLIP is critical for their deployment in safety-critical applications like autonomous driving, healthcare diagnostics, and security systems, where accurate interpretation of visual and…
Multi-modal foundation models like OpenFlamingo, LLaVA, and GPT-4 are increasingly used for various real-world tasks. Prior work has shown that these models are highly vulnerable to adversarial attacks on the vision modality. These attacks…
Vision-language models (VLMs), such as CLIP, have demonstrated exceptional generalization capabilities and can quickly adapt to downstream tasks through prompt fine-tuning. Unfortunately, in classification tasks involving non-training…
Despite its prevalent use in image-text matching tasks in a zero-shot manner, CLIP has been shown to be highly vulnerable to adversarial perturbations added onto images. Recent studies propose to finetune the vision encoder of CLIP with…
Vision-Language Models (VLMs), such as CLIP, exhibit strong image-text comprehension abilities, facilitating advances in several downstream tasks such as zero-shot image classification, image-text retrieval, and text-to-image generation.…
Pre-trained multi-modal Vision-Language Models like CLIP are widely used off-the-shelf for a variety of applications. In this paper, we show that the common practice of individually exploiting the text or image encoders of these powerful…
Cross-modal alignment aims to map heterogeneous modalities into a shared latent space, as exemplified by models like CLIP, which benefit from large-scale image-text pretraining for strong recognition capabilities. However, when operating in…
Contrastive Language-Image Pre-training (CLIP) models have shown significant potential, particularly in zero-shot classification across diverse distribution shifts. Building on existing evaluations of overall classification robustness, this…
Vision-Language Models (VLMs) rely heavily on pretrained vision encoders to support downstream tasks such as image captioning, visual question answering, and zero-shot classification. Despite their strong performance, these encoders remain…
Few-shot learning (FSL) often requires effective adaptation of models using limited labeled data. However, most existing FSL methods rely on entangled representations, requiring the model to implicitly recover the unmixing process to obtain…
Contrastive language image pre-training (CLIP) is an essential component of building modern vision-language foundation models. While CLIP demonstrates remarkable zero-shot performance on downstream tasks, the multi-modal feature spaces…
Deep Learning (DL) is undergoing a paradigm shift with the emergence of foundation models. In this work, we focus on Contrastive Language-Image Pre-training (CLIP), a Vision-Language foundation model that achieves high accuracy across…
Vision-Language Models (VLMs) such as CLIP learn a shared embedding space for images and text, yet their representations remain geometrically separated, a phenomenon known as the modality gap. This gap limits tasks requiring cross-modal…
The learning objective of vision-language approach of CLIP does not effectively account for the noisy many-to-many correspondences found in web-harvested image captioning datasets, which contributes to its compute and data inefficiency. To…
Foundation models like CLIP allow zero-shot transfer on various tasks without additional training data. Yet, the zero-shot performance is less competitive than a fully supervised one. Thus, to enhance the performance, fine-tuning and…
This paper investigates the robustness of vision-language models against adversarial visual perturbations and introduces a novel ``double visual defense" to enhance this robustness. Unlike previous approaches that resort to lightweight…
Pretrained large-scale vision-language models like CLIP have exhibited strong generalization over unseen tasks. Yet imperceptible adversarial perturbations can significantly reduce CLIP's performance on new tasks. In this work, we identify…