中文
相关论文

相关论文: On the Potential of CLIP for Compositional Logical…

200 篇论文

OpenAI's CLIP, released in early 2021, have long been the go-to choice of vision encoder for building multimodal foundation models. Although recent alternatives such as SigLIP have begun to challenge this status quo, to our knowledge none…

计算机视觉与模式识别 · 计算机科学 2025-05-08 Xianhang Li , Yanqing Liu , Haoqin Tu , Hongru Zhu , Cihang Xie

Human cognition exhibits systematic compositionality, the algebraic ability to generate infinite novel combinations from finite learned components, which is the key to understanding and reasoning about complex logic. In this work, we…

计算与语言 · 计算机科学 2024-10-11 Jun Zhao , Jingqi Tong , Yurong Mou , Ming Zhang , Qi Zhang , Xuanjing Huang

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…

计算机视觉与模式识别 · 计算机科学 2026-05-08 Chenyang Zhao , Kun Wang , Janet H. Hsiao , Antoni B. Chan

Despite its prevalent use in image-text matching tasks in a zero-shot manner, CLIP has been shown to be highly vulnerable to adversarial perturbations added onto images. Recent studies propose to finetune the vision encoder of CLIP with…

计算机视觉与模式识别 · 计算机科学 2025-03-06 Songlong Xing , Zhengyu Zhao , Nicu Sebe

Large-scale vision-language models like CLIP have demonstrated impressive open-vocabulary capabilities for image-level tasks, excelling in recognizing what objects are present. However, they struggle with pixel-level recognition tasks like…

计算机视觉与模式识别 · 计算机科学 2024-10-01 Heeseong Shin , Chaehyun Kim , Sunghwan Hong , Seokju Cho , Anurag Arnab , Paul Hongsuck Seo , Seungryong Kim

This work presents CLIPDraw, an algorithm that synthesizes novel drawings based on natural language input. CLIPDraw does not require any training; rather a pre-trained CLIP language-image encoder is used as a metric for maximizing…

计算机视觉与模式识别 · 计算机科学 2021-06-29 Kevin Frans , L. B. Soros , Olaf Witkowski

A sliding-window inference strategy is commonly adopted in recent training-free open-vocabulary semantic segmentation methods to overcome limitation of the CLIP in processing high-resolution images. However, this approach introduces a new…

计算机视觉与模式识别 · 计算机科学 2026-03-25 ByeongCheol Lee , Hyun Seok Seong , Sangeek Hyun , Gilhan Park , WonJun Moon , Jae-Pil Heo

Traditional Artificial Cognitive Systems (for example, intelligent robots) share a number of limitations. First, they are usually made up only of machine components; humans are only playing the role of user or supervisor. And yet, there are…

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

This short technical report demonstrates a simple technique that yields state of the art results in medical image-text matching tasks. We analyze the use of OpenAI's CLIP, a general image-text matching model, and observe that CLIP's limited…

机器学习 · 计算机科学 2023-03-24 Idan Glassberg , Tom Hope

Understanding when and why to apply any given eXplainable Artificial Intelligence (XAI) technique is not a straightforward task. There is no single approach that is best suited for a given context. This paper aims to address the challenge…

人工智能 · 计算机科学 2023-12-14 Leila Methnani , Virginia Dignum , Andreas Theodorou

Explainable AI(XAI)is a domain focused on providing interpretability and explainability of a decision-making process. In the domain of law, in addition to system and data transparency, it also requires the (legal-) decision-model…

人机交互 · 计算机科学 2020-12-18 Lukasz Gorski , Shashishekar Ramakrishna , Jedrzej M. Nowosielski

Face recognition is a core task in computer vision designed to identify and authenticate individuals by analyzing facial patterns and features. This field intersects with artificial intelligence image processing and machine learning with…

计算机视觉与模式识别 · 计算机科学 2024-11-21 Nhan T. Luu

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

Image captioning is a fundamental task in vision-language understanding, where the model predicts a textual informative caption to a given input image. In this paper, we present a simple approach to address this task. We use CLIP encoding…

计算机视觉与模式识别 · 计算机科学 2021-11-19 Ron Mokady , Amir Hertz , Amit H. Bermano

Recent works utilize CLIP to perform the challenging unsupervised semantic segmentation task where only images without annotations are available. However, we observe that when adopting CLIP to such a pixel-level understanding task,…

计算机视觉与模式识别 · 计算机科学 2026-05-11 Jingyun Wang , Guoliang Kang

Existing vision-language models (VLMs) such as CLIP have showcased an impressive capability to generalize well across various downstream tasks. These models leverage the synergy between visual and textual information, enabling them to…

计算机视觉与模式识别 · 计算机科学 2025-05-27 Fangming Cui , Yonggang Zhang , Xuan Wang , Xule Wang , Liang Xiao

In this work, we present a conceptually simple and effective method to train a strong bilingual/multilingual multimodal representation model. Starting from the pre-trained multimodal representation model CLIP released by OpenAI, we altered…

计算与语言 · 计算机科学 2022-11-22 Zhongzhi Chen , Guang Liu , Bo-Wen Zhang , Fulong Ye , Qinghong Yang , Ledell Wu

In rapidly evolving field of vision-language models (VLMs), contrastive language-image pre-training (CLIP) has made significant strides, becoming foundation for various downstream tasks. However, relying on one-to-one (image, text)…

计算机视觉与模式识别 · 计算机科学 2024-12-03 Haicheng Wang , Chen Ju , Weixiong Lin , Shuai Xiao , Mengting Chen , Yixuan Huang , Chang Liu , Mingshuai Yao , Jinsong Lan , Ying Chen , Qingwen Liu , Yanfeng Wang

Recent strides in multimodal model development have ignited a paradigm shift in the realm of text-to-image generation. Among these advancements, CLIP stands out as a remarkable achievement which is a sophisticated autoencoder adept at…

人工智能 · 计算机科学 2026-01-07 Abdul Aziz A. B , A. B Abdul Rahim