相关论文: Efficient Discriminative Joint Encoders for Large …

We introduce SigLIP 2, a family of new multilingual vision-language encoders that build on the success of the original SigLIP. In this second iteration, we extend the original image-text training objective with several prior, independently…

Recent advancements in Large Vision-Language Models (LVLMs) have significantly expanded their utility in tasks like image captioning and visual question answering. However, they still struggle with object hallucination, where models…

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…

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…

Slide decks, serving as digital reports that bridge the gap between presentation slides and written documents, are a prevalent medium for conveying information in both academic and corporate settings. Their multimodal nature, combining…

Recent vision-language models excel at large-scale image-text alignment but often neglect the compositional structure of language, leading to failures on tasks that hinge on word order and predicate-argument structure. We introduce…

Recent multimodal large language models are computationally expensive because Transformers must process a large number of visual tokens. We present ReDiPrune, a training-free token pruning method applied before the vision-language…

Vision transformers in vision-language models typically use the same amount of compute for every image, regardless of whether it is simple or complex. We propose ICAR (Image Complexity-Aware Retrieval), an adaptive computation approach that…

Multimodal documents contain diverse elements, such as tables, figures, and layouts, which can complicate retrieval tasks. While current approaches typically combine dense visual embedding models with supervised rerankers to achieve…

In the rapidly advancing field of image generation, Visual Auto-Regressive (VAR) modeling has garnered considerable attention for its innovative next-scale prediction approach. This paradigm offers substantial improvements in efficiency,…

Visual token pruning aims to compress and prune redundant visual tokens which play a critical role in efficient inference with large vision-language models (LVLMs). However, most existing work estimates visual redundancy using a single…

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…

Contrastive language image pretraining (CLIP) encoders have been shown to be beneficial for a range of visual tasks from classification and detection to captioning and image manipulation. We investigate the effectiveness of CLIP visual…

Contrastive image-text pre-trained models such as CLIP have shown remarkable adaptability to downstream tasks. However, they face challenges due to the high computational requirements of the Vision Transformer (ViT) backbone. Current…

Fine-grained image classification, the task of distinguishing between visually similar subcategories within a broader category (e.g., bird species, car models, flower types), is a challenging computer vision problem. Traditional approaches…

Dense retrievers encode queries and documents and map them in an embedding space using pre-trained language models. These embeddings need to be high-dimensional to fit training signals and guarantee the retrieval effectiveness of dense…

In recent years, layered image compression is demonstrated to be a promising direction, which encodes a compact representation of the input image and apply an up-sampling network to reconstruct the image. To further improve the quality of…

As a pioneering vision-language model, CLIP (Contrastive Language-Image Pre-training) has achieved significant success across various domains and a wide range of downstream vision-language tasks. However, the text encoders in popular CLIP…

Contrastive learning has emerged as a transformative method for learning effective visual representations through the alignment of image and text embeddings. However, pairwise similarity computation in contrastive loss between image and…

Image-text retrieval requires the system to bridge the heterogenous gap between vision and language for accurate retrieval while keeping the network lightweight-enough for efficient retrieval. Existing trade-off solutions mainly study from…