Related papers: Explaining, Verifying, and Aligning Semantic Hiera…

This paper introduces VLAP, a novel approach that bridges pretrained vision models and large language models (LLMs) to make frozen LLMs understand the visual world. VLAP transforms the embedding space of pretrained vision models into the…

Vision-language models (VLMs) such as CLIP are trained via contrastive learning between text and image pairs, resulting in aligned image and text embeddings that are useful for many downstream tasks. A notable drawback of CLIP, however, is…

Current Large Vision Language Models (LVLMs) excel at many zero-shot tasks like image captioning, visual question answering and OCR. However, these same models suffer from poor performance at image classification tasks, underperforming…

Aligned text-image encoders such as CLIP have become the de facto model for vision-language tasks. Furthermore, modality-specific encoders achieve impressive performances in their respective domains. This raises a central question: does an…

Accurately describing images with text is a foundation of explainable AI. Vision-Language Models (VLMs) like CLIP have recently addressed this by aligning images and texts in a shared embedding space, expressing semantic similarities…

Vision-language models (VLMs) like CLIP have been cherished for their ability to perform zero-shot visual recognition on open-vocabulary concepts. This is achieved by selecting the object category whose textual representation bears the…

Vision-language models (VLM) align images and text in a shared representation space that is useful for retrieval and zero-shot transfer. Yet, this alignment can encode and amplify social stereotypes in subtle ways that are not obvious from…

The zero-shot performance of existing vision-language models (VLMs) such as CLIP is limited by the availability of large-scale, aligned image and text datasets in specific domains. In this work, we leverage two complementary sources of…

Aligning visual features with language embeddings is a key challenge in vision-language models (VLMs). The performance of such models hinges on having a good connector that maps visual features generated by a vision encoder to a shared…

Pre-trained vision-language models, e.g., CLIP, have been successfully applied to zero-shot semantic segmentation. Existing CLIP-based approaches primarily utilize visual features from the last layer to align with text embeddings, while…

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…

A challenge in advancing Visual-Language Models (VLMs) is determining whether their failures on abstract reasoning tasks, such as Bongard problems, stem from flawed perception or faulty top-down reasoning. To disentangle these factors, we…

How well do text-only large language models (LLMs) align with the visual world? We present a systematic evaluation of this question by incorporating frozen representations of various language models into a discriminative vision-language…

Object categories are typically organized into a multi-granularity taxonomic hierarchy. When classifying categories at different hierarchy levels, traditional uni-modal approaches focus primarily on image features, revealing limitations in…

Recent approaches have shown that training deep neural networks directly on large-scale image-text pair collections enables zero-shot transfer on various recognition tasks. One central issue is how this can be generalized to object…

Models that bridge vision and language, such as CLIP, are key components of multimodal AI, yet their large-scale, uncurated training data introduce severe social and spurious biases. Existing post-hoc debiasing methods often operate…

Recent work shows that documents from encyclopedias serve as helpful auxiliary information for zero-shot learning. Existing methods align the entire semantics of a document with corresponding images to transfer knowledge. However, they…

The pre-trained vision-language model, exemplified by CLIP, advances zero-shot semantic segmentation by aligning visual features with class embeddings through a transformer decoder to generate semantic masks. Despite its effectiveness,…

Recent generalist vision-language models (VLMs) have demonstrated impressive reasoning capabilities across diverse multimodal tasks. However, these models still struggle with fine-grained object-level understanding and grounding. In terms…

It has recently been discovered that using a pre-trained vision-language model (VLM), e.g., CLIP, to align a whole query image with several finer text descriptions generated by a large language model can significantly enhance zero-shot…