相关论文: Text-To-Concept (and Back) via Cross-Model Alignme…

Vision-language pretraining on large datasets of images-text pairs is one of the main building blocks of current Vision-Language Models. While with additional training, these models excel in various downstream tasks, including visual…

We investigate the CLIP image encoder by analyzing how individual model components affect the final representation. We decompose the image representation as a sum across individual image patches, model layers, and attention heads, and use…

Contrastive Language-Image Pretraining (CLIP) achieves strong generalization in vision-language tasks by aligning images and texts in a shared embedding space. However, recent findings show that CLIP-like models still underutilize…

We introduce NOVIC, an innovative real-time uNconstrained Open Vocabulary Image Classifier that uses an autoregressive transformer to generatively output classification labels as language. Leveraging the extensive knowledge of CLIP models,…

Training a text-to-image generator in the general domain (e.g., Dall.e, CogView) requires huge amounts of paired text-image data, which is too expensive to collect. In this paper, we propose a self-supervised scheme named as CLIP-GEN for…

Recent text-to-image matching models apply contrastive learning to large corpora of uncurated pairs of images and sentences. While such models can provide a powerful score for matching and subsequent zero-shot tasks, they are not capable of…

VAR is a new generation paradigm that employs 'next-scale prediction' as opposed to 'next-token prediction'. This innovative transformation enables auto-regressive (AR) transformers to rapidly learn visual distributions and achieve robust…

Our understanding of the visual world is centered around various concept axes, characterizing different aspects of visual entities. While different concept axes can be easily specified by language, e.g. color, the exact visual nuances along…

Pre-trained vision-language models like CLIP have recently shown superior performances on various downstream tasks, including image classification and segmentation. However, in fine-grained image re-identification (ReID), the labels are…

CLIP models learn transferable multi-modal features via image-text contrastive learning on internet-scale data. They are widely used in zero-shot classification, multi-modal retrieval, text-to-image diffusion, and as image encoders in large…

There are a thousand ways to caption an image. Contrastive Language Pretraining (CLIP) on the other hand, works by mapping an image and its caption to a single vector -- limiting how well CLIP-like models can represent the diverse ways to…

Vision-language models like CLIP are widely used in zero-shot image classification due to their ability to understand various visual concepts and natural language descriptions. However, how to fully leverage CLIP's unprecedented human-like…

We describe a protocol to study text-to-video retrieval training with unlabeled videos, where we assume (i) no access to labels for any videos, i.e., no access to the set of ground-truth captions, but (ii) access to labeled images in the…

Contrastive vision-language models, such as CLIP, have demonstrated excellent zero-shot capability across semantic recognition tasks, mainly attributed to the training on a large-scale I&1T (one Image with one Text) dataset. This kind of…

Vision-language pre-training like CLIP has shown promising performance on various downstream tasks such as zero-shot image classification and image-text retrieval. Most of the existing CLIP-alike works usually adopt relatively large image…

This work explores text-to-image retrieval for queries that specify or describe a semantic category. While vision-and-language models (VLMs) like CLIP offer a straightforward open-vocabulary solution, they map text and images to distant…

Contrastive Language-Image Pre-training (CLIP) has become a foundation model and has been applied to various vision and multimodal tasks. However, recent works indicate that CLIP falls short in distinguishing detailed differences in images…

Significant progress has been achieved on the improvement and downstream usages of the Contrastive Language-Image Pre-training (CLIP) vision-language model, while less attention is paid to the interpretation of CLIP. We propose a…

Large-scale pre-trained image-text models demonstrate remarkable versatility across diverse tasks, benefiting from their robust representational capabilities and effective multimodal alignment. We extend the application of these models,…

Contrastive Language-Image Pre-training (CLIP) formulates image classification as an image-to-text matching task, i.e., matching images to the corresponding natural language descriptions instead of discrete category IDs. This allows for…