相关论文: Reevaluating the Intra-Modal Misalignment Hypothes…

CLIP outperforms self-supervised models like DINO as vision encoders for vision-language models (VLMs), but it remains unclear whether this advantage stems from CLIP's language supervision or its much larger training data. To disentangle…

Pretrained vision-language models such as CLIP achieve strong zero-shot generalization but remain vulnerable to distribution shifts caused by input corruptions. In this work, we investigate how corruptions affect CLIP's image embeddings and…

Vision-language models like CLIP have shown impressive capabilities in aligning images and text, but they often struggle with lengthy and detailed text descriptions because of their training focus on short and concise captions. We present…

Image clustering is an important and open-challenging task in computer vision. Although many methods have been proposed to solve the image clustering task, they only explore images and uncover clusters according to the image features, thus…

Large pre-trained vision-language models, such as CLIP, have demonstrated state-of-the-art performance across a wide range of image classification tasks, without requiring retraining. Few-shot CLIP is competitive with existing specialized…

CLIP (Contrastive Language-Image Pre-Training) has shown remarkable zero-shot transfer capabilities in cross-modal correlation tasks such as visual classification and image retrieval. However, its performance in cross-modal generation tasks…

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…

Recent research in cross-lingual word embeddings has almost exclusively focused on offline methods, which independently train word embeddings in different languages and map them to a shared space through linear transformations. While…

Contrastive Language-Image Pretraining (CLIP) has emerged as a novel paradigm to learn visual models from language supervision. While researchers continue to push the frontier of CLIP, reproducing these works remains challenging. This is…

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…

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…

Multimodal search has revolutionized the fashion industry, providing a seamless and intuitive way for users to discover and explore fashion items. Based on their preferences, style, or specific attributes, users can search for products by…

Recently, the cross-modal pretraining model has been employed to produce meaningful pseudo-labels to supervise the training of an image clustering model. However, numerous erroneous alignments in a cross-modal pre-training model could…

Fine-tuning pre-trained vision-language models, like CLIP, has yielded success on diverse downstream tasks. However, several pain points persist for this paradigm: (i) directly tuning entire pre-trained models becomes both time-intensive…

Recent significant advances in text-to-image models unlock the possibility of training vision systems using synthetic images, potentially overcoming the difficulty of collecting curated data at scale. It is unclear, however, how these…

In recent years, vision and language pre-training (VLP) models have advanced the state-of-the-art results in a variety of cross-modal downstream tasks. Aligning cross-modal semantics is claimed to be one of the essential capabilities of VLP…

We explore the extent to which zero-shot vision-language models exhibit gender bias for different vision tasks. Vision models traditionally required task-specific labels for representing concepts, as well as finetuning; zero-shot models…

Existing contrastive language-image pre-training aims to learn a joint representation by matching abundant image-text pairs. However, the number of image-text pairs in medical datasets is usually orders of magnitude smaller than that in…

Multimodal contrastive learning (MCL) aims to embed data from different modalities in a shared embedding space. However, empirical evidence shows that representations from different modalities occupy completely separate regions of embedding…

Multi-label image classification is a foundational topic in various domains. Multimodal learning approaches have recently achieved outstanding results in image representation and single-label image classification. For instance, Contrastive…