相关论文: Common Data Properties Limit Object-Attribute Bind…

CLIP has demonstrated exceptional image-text matching capabilities due to its training on contrastive learning tasks. Past research has suggested that whereas CLIP effectively matches text to images when the matching can be achieved just by…

Vision-language models like CLIP excel at recognizing the single, prominent object in a scene. However, they struggle in complex scenes containing multiple objects. We identify a fundamental reason for this limitation: VLM feature space…

We investigate the success conditions for compositional generalization of CLIP models on real-world data through performance prediction. Prior work shows that CLIP requires exponentially more pretraining data for linear performance gains on…

A common problem in contextual preference ranking is that a single preferred action is compared against several choices, thereby blowing up the complexity and skewing the preference distribution. In this work, we show how one can solve this…

Contrastive Language-Image Pre-training (CLIP) learns rich representations via readily available supervision of natural language. It improves the performance of downstream vision tasks, including but not limited to the zero-shot, long tail,…

Household environments are visually diverse. Embodied agents performing Vision-and-Language Navigation (VLN) in the wild must be able to handle this diversity, while also following arbitrary language instructions. Recently, Vision-Language…

For video captioning, "pre-training and fine-tuning" has become a de facto paradigm, where ImageNet Pre-training (INP) is usually used to encode the video content, then a task-oriented network is fine-tuned from scratch to cope with caption…

Dense visual prediction tasks have been constrained by their reliance on predefined categories, limiting their applicability in real-world scenarios where visual concepts are unbounded. While Vision-Language Models (VLMs) like CLIP have…

The remarkable generalization performance of contrastive vision-language models like CLIP is often attributed to the diversity of their training distributions. However, key questions remain unanswered: Can CLIP generalize to an entirely…

Contrastive language image pretraining (CLIP) is a standard method for training vision-language models. While CLIP is scalable, promptable, and robust to distribution shifts on image classification tasks, it lacks object localization…

The interplay between the image and comment on a social media post is one of high importance for understanding its overall message. Recent strides in multimodal embedding models, namely CLIP, have provided an avenue forward in relating…

Contrastive Language-Image Pre-training (CLIP) stands as one of the most effective and scalable methods for training transferable vision models using paired image and text data. CLIP models are trained using contrastive loss, which…

CLIP has demonstrated great versatility in adapting to various downstream tasks, such as image editing and generation, visual question answering, and video understanding. However, CLIP-based applications often suffer from misunderstandings…

Contrastive Language-Image Pretraining (CLIP) has achieved remarkable success, leading to rapid advancements in multimodal studies. However, CLIP faces a notable challenge in terms of inefficient data utilization. It relies on a single…

Despite the success of Vision-Language Models (VLMs) like CLIP in aligning vision and language, their proficiency in detailed, fine-grained visual comprehension remains a key challenge. We present CLIP-IN, a novel framework that bolsters…

The development of CLIP [Radford et al., 2021] has sparked a debate on whether language supervision can result in vision models with more transferable representations than traditional image-only methods. Our work studies this question…

Contrastive Language-Image Pretraining (CLIP) has achieved remarkable success in cross-modal tasks such as zero-shot image classification and text-image retrieval by effectively aligning visual and textual representations. However, the…

Self-supervised models trained with a contrastive loss such as CLIP have shown to be very powerful in zero-shot classification settings. However, to be used as a zero-shot classifier these models require the user to provide new captions…

Contrastive Language-Image Pre-Training (CLIP) is highly instrumental in machine learning applications within a large variety of domains. We investigate the geometry of this embedding, which is still not well understood. We examine the raw…

Vision-language models, such as contrastive language-image pre-training (CLIP), have demonstrated impressive results in natural image domains. However, these models often struggle when applied to specialized domains like remote sensing, and…