Related papers: Quantifying and Enabling the Interpretability of C…

CLIP is a widely used foundational vision-language model that is used for zero-shot image recognition and other image-text alignment tasks. We demonstrate that CLIP is vulnerable to change in image quality under compression. This surprising…

Large-scale pre-trained vision foundation models, such as CLIP, have become de facto backbones for various vision tasks. However, due to their black-box nature, understanding the underlying rules behind these models' predictions and…

Pre-trained vision-language (V-L) models such as CLIP have shown excellent generalization ability to downstream tasks. However, they are sensitive to the choice of input text prompts and require careful selection of prompt templates to…

Despite remarkable advancements in supervised pansharpening neural networks, these methods face domain adaptation challenges of resolution due to the intrinsic disparity between simulated reduced-resolution training data and real-world…

Contrastive Vision-Language Pre-training(CLIP) demonstrates impressive zero-shot capability. The key to improve the adaptation of CLIP to downstream task with few exemplars lies in how to effectively model and transfer the useful knowledge…

Vision-Language Models (VLMs) demonstrate remarkable capabilities in visual understanding and reasoning, such as in Visual Question Answering (VQA), where the model is asked a question related to a visual input. Still, these models can make…

Training models to apply linguistic knowledge and visual concepts from 2D images to 3D world understanding is a promising direction that researchers have only recently started to explore. In this work, we design a novel 3D pre-training…

Transformer-based CLIP models are widely used for text-image probing and feature extraction, making it relevant to understand the internal mechanisms behind their predictions. While recent works show that Sparse Autoencoders (SAEs) yield…

Neural NLP models are increasingly accurate but are imperfect and opaque---they break in counterintuitive ways and leave end users puzzled at their behavior. Model interpretation methods ameliorate this opacity by providing explanations for…

The integration of human and artificial intelligence offers a powerful avenue for advancing our understanding of information processing, as each system provides unique computational insights. However, despite the promise of human-AI…

Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated remarkable progress in visual understanding. This impressive leap raises a compelling question: how can language models, initially trained solely on…

Contrastive Language-Image Pre-training (CLIP) has been a celebrated method for training vision encoders to generate image/text representations facilitating various applications. Recently, CLIP has been widely adopted as the vision backbone…

Contrastive Language-Image Pre-training (CLIP) represents the latest incarnation of pre-trained vision-language models. Although CLIP has recently shown its superior power on a wide range of downstream vision-language tasks like Visual…

The process of transforming input images into corresponding textual explanations stands as a crucial and complex endeavor within the domains of computer vision and natural language processing. In this paper, we propose an innovative…

Photo search, the task of retrieving images based on textual queries, has witnessed significant advancements with the introduction of CLIP (Contrastive Language-Image Pretraining) model. CLIP leverages a vision-language pre training…

Large-scale vision-language models demonstrate strong multimodal alignment and generalization across diverse tasks. Among them, CLIP stands out as one of the most successful approaches. In this work, we extend the application of CLIP to…

This paper investigates the role of attention heads in CLIP's image encoder. Building on interpretability studies, we conduct an exhaustive analysis and find that certain heads, distributed across layers, are detrimental to the resulting…

Contrastive language-image models such as CLIP have demonstrated remarkable generalization capabilities. However, how their internal visual representations evolve during training and how this evolution relates to human perception remains…

Multimodal sentiment analysis is an important area for understanding the user's internal states. Deep learning methods were effective, but the problem of poor interpretability has gradually gained attention. Previous works have attempted to…

Multimodal models, such as the Contrastive Language-Image Pre-training (CLIP) model, have demonstrated remarkable success in aligning visual and linguistic representations. However, these models exhibit limitations when applied to…