中文
相关论文

相关论文: C-CLIP: Contrastive Image-Text Encoders to Close t…

200 篇论文

Treating texts as images, combining prompts with textual labels for prompt tuning, and leveraging the alignment properties of CLIP have been successfully applied in zero-shot multi-label image recognition. Nonetheless, relying solely on…

计算机视觉与模式识别 · 计算机科学 2024-07-09 Haonan Xu , Dian Chao , Xiangyu Wu , Zhonghua Wan , Yang Yang

Recent advances in vision language models (VLM) have been driven by contrastive models such as CLIP, which learn to associate visual information with their corresponding text descriptions. However, these models have limitations in…

计算机视觉与模式识别 · 计算机科学 2025-02-21 Rim Assouel , Pietro Astolfi , Florian Bordes , Michal Drozdzal , Adriana Romero-Soriano

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…

计算机视觉与模式识别 · 计算机科学 2022-07-18 Shibani Santurkar , Yann Dubois , Rohan Taori , Percy Liang , Tatsunori Hashimoto

Most existing Vision-and-Language (V&L) models rely on pre-trained visual encoders, using a relatively small set of manually-annotated data (as compared to web-crawled data), to perceive the visual world. However, it has been observed that…

计算机视觉与模式识别 · 计算机科学 2021-07-15 Sheng Shen , Liunian Harold Li , Hao Tan , Mohit Bansal , Anna Rohrbach , Kai-Wei Chang , Zhewei Yao , Kurt Keutzer

CLIP (Contrastive Language-Image Pretraining) has become a popular choice for various downstream tasks. However, recent studies have questioned its ability to represent compositional concepts effectively. These works suggest that CLIP often…

计算机视觉与模式识别 · 计算机科学 2026-03-03 Darina Koishigarina , Arnas Uselis , Seong Joon Oh

The inexorable growth of online shopping and e-commerce demands scalable and robust machine learning-based solutions to accommodate customer requirements. In the context of automatic tagging classification and multimodal retrieval, prior…

计算机视觉与模式识别 · 计算机科学 2023-09-12 Giuseppe Cartella , Alberto Baldrati , Davide Morelli , Marcella Cornia , Marco Bertini , Rita Cucchiara

The recent large-scale Contrastive Language-Image Pretraining (CLIP) model has shown great potential in various downstream tasks via leveraging the pretrained vision and language knowledge. Scene text, which contains rich textual and visual…

计算机视觉与模式识别 · 计算机科学 2023-03-28 Wenwen Yu , Yuliang Liu , Wei Hua , Deqiang Jiang , Bo Ren , Xiang Bai

Multimodal models are becoming increasingly effective, in part due to unified components, such as the Transformer architecture. However, multimodal models still often consist of many task- and modality-specific pieces and training…

计算机视觉与模式识别 · 计算机科学 2023-04-04 Michael Tschannen , Basil Mustafa , Neil Houlsby

Image captioning, a.k.a. "image-to-text," which generates descriptive text from given images, has been rapidly developing throughout the era of deep learning. To what extent is the information in the original image preserved in the…

计算机视觉与模式识别 · 计算机科学 2023-05-12 Honori Udo , Takafumi Koshinaka

Self-supervised contrastive learning models, such as CLIP, have set new benchmarks for vision-language models in many downstream tasks. However, their dependency on rigid one-to-one mappings overlooks the complex and often multifaceted…

计算机视觉与模式识别 · 计算机科学 2025-03-25 Yiming Zhang , Zhuokai Zhao , Zhaorun Chen , Zhili Feng , Zenghui Ding , Yining Sun

Dual encoder architectures like Clip models map two types of inputs into a shared embedding space and predict similarities between them. Despite their wide application, it is, however, not understood how these models compare their two…

计算机视觉与模式识别 · 计算机科学 2025-08-14 Lucas Möller , Pascal Tilli , Ngoc Thang Vu , Sebastian Padó

Visual imagery does not consist of solitary objects, but instead reflects the composition of a multitude of fluid concepts. While there have been great advances in visual representation learning, such advances have focused on building…

计算机视觉与模式识别 · 计算机科学 2025-04-07 Austin Stone , Hagen Soltau , Robert Geirhos , Xi Yi , Ye Xia , Bingyi Cao , Kaifeng Chen , Abhijit Ogale , Jonathon Shlens

Performant vision-language (VL) models like CLIP represent captions using a single vector. How much information about language is lost in this bottleneck? We first curate CompPrompts, a set of increasingly compositional image captions that…

计算与语言 · 计算机科学 2023-10-31 Amita Kamath , Jack Hessel , Kai-Wei Chang

The effectiveness of Contrastive Language-Image Pre-training (CLIP) models critically depends on the semantic diversity and quality of their training data. However, while existing synthetic data generation methods primarily focus on…

计算机视觉与模式识别 · 计算机科学 2025-11-10 Yuanxiang Huangfu , Chaochao Wang , Weilei Wang

The explosion of data has resulted in more and more associated text being transmitted along with images. Inspired by from distributed source coding, many works utilize image side information to enhance image compression. However, existing…

计算机视觉与模式识别 · 计算机科学 2023-11-29 Shiyu Qin , Bin Chen , Yujun Huang , Baoyi An , Tao Dai , Shu-Tao Xia

Contrastive learning has emerged as an efficient framework to learn multimodal representations. CLIP, a seminal work in this area, achieved impressive results by training on paired image-text data using the contrastive loss. Recent work…

计算机视觉与模式识别 · 计算机科学 2023-11-07 Enrico Fini , Pietro Astolfi , Adriana Romero-Soriano , Jakob Verbeek , Michal Drozdzal

Contrastive Language-Image Pretraining (CLIP) is a popular foundation model, supporting from zero-shot classification, retrieval to encoders for multimodal large language models (MLLMs). Although CLIP is successfully trained on…

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…

计算机视觉与模式识别 · 计算机科学 2024-11-26 Prithviraj Purushottam Naik , Rohit Agarwal

CLIP (Contrastive Language-Image Pre-training) has attained great success in pattern recognition and computer vision. Transferring CLIP to downstream tasks (e.g. zero- or few-shot classification) is a hot topic in multimodal learning.…

计算机视觉与模式识别 · 计算机科学 2025-01-22 Zhipeng Ye , Feng Jiang , Qiufeng Wang , Kaizhu Huang , Jiaqi Huang

Large-scale pre-trained Vision-Language Models (VLMs), such as CLIP, establish the correlation between texts and images, achieving remarkable success on various downstream tasks with fine-tuning. In existing fine-tuning methods, the…

计算机视觉与模式识别 · 计算机科学 2023-07-31 Yi Zhang , Ce Zhang , Yushun Tang , Zhihai He