English
Related papers

Related papers: How Much Can CLIP Benefit Vision-and-Language Task…

200 papers

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…

Computer Vision and Pattern Recognition · Computer Science 2022-04-18 Apoorv Khandelwal , Luca Weihs , Roozbeh Mottaghi , Aniruddha Kembhavi

Contrastive Language-Image Pretraining (CLIP) models maximize the mutual information between text and visual modalities to learn representations. This makes the nature of the training data a significant factor in the efficacy of CLIP for…

Computer Vision and Pattern Recognition · Computer Science 2024-11-06 Maitreya Patel , Abhiram Kusumba , Sheng Cheng , Changhoon Kim , Tejas Gokhale , Chitta Baral , Yezhou Yang

The original CLIP text encoder is limited by a maximum input length of 77 tokens, which hampers its ability to effectively process long texts and perform fine-grained semantic understanding. In addition, the CLIP text encoder lacks support…

Computer Vision and Pattern Recognition · Computer Science 2026-01-08 Xiaoxing Hu , Kaicheng Yang , Ziyang Gong , Qi Ming , Zonghao Guo , Yu Tian , Xiang An , Ziyong Feng , Xue Yang

Few-shot segmentation remains challenging due to the limitations of its labeling information for unseen classes. Most previous approaches rely on extracting high-level feature maps from the frozen visual encoder to compute the pixel-wise…

Computer Vision and Pattern Recognition · Computer Science 2024-05-15 Jin Wang , Bingfeng Zhang , Jian Pang , Honglong Chen , Weifeng Liu

Contrastive Language-Image Pre-training (CLIP) has been shown to improve zero-shot generalization capabilities of language and vision models. In this paper, we extend CLIP for efficient knowledge distillation, by utilizing embeddings as…

Machine Learning · Computer Science 2024-09-02 Lakshmi Nair

Masked language modeling (MLM) has been one of the most popular pretraining recipes in natural language processing, e.g., BERT, one of the representative models. Recently, contrastive language-image pretraining (CLIP) has also attracted…

Computation and Language · Computer Science 2023-06-07 Zhihong Chen , Guiming Hardy Chen , Shizhe Diao , Xiang Wan , Benyou Wang

The performance of vision-language models (VLMs), such as CLIP, in visual classification tasks, has been enhanced by leveraging semantic knowledge from large language models (LLMs), including GPT. Recent studies have shown that in zero-shot…

Computer Vision and Pattern Recognition · Computer Science 2024-11-12 Hankyeol Lee , Gawon Seo , Wonseok Choi , Geunyoung Jung , Kyungwoo Song , Jiyoung Jung

Contrastive Language-Image Pre-training (CLIP), which excels at abstracting open-world representations across domains and modalities, has become a foundation for a variety of vision and multimodal tasks. However, recent studies reveal that…

Computer Vision and Pattern Recognition · Computer Science 2024-08-27 Wenxuan Wang , Quan Sun , Fan Zhang , Yepeng Tang , Jing Liu , Xinlong Wang

Training models to apply common-sense linguistic knowledge and visual concepts from 2D images to 3D scene understanding is a promising direction that researchers have only recently started to explore. However, it still remains understudied…

Computer Vision and Pattern Recognition · Computer Science 2023-06-12 Alexandros Delitzas , Maria Parelli , Nikolas Hars , Georgios Vlassis , Sotirios Anagnostidis , Gregor Bachmann , Thomas Hofmann

Vision-language pre-training methods, e.g., CLIP, demonstrate an impressive zero-shot performance on visual categorizations with the class proxy from the text embedding of the class name. However, the modality gap between the text and…

Computer Vision and Pattern Recognition · Computer Science 2023-10-31 Qi Qian , Yuanhong Xu , Juhua Hu

Video understanding has shown remarkable improvements in recent years, largely dependent on the availability of large scaled labeled datasets. Recent advancements in visual-language models, especially based on contrastive pretraining, have…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Shreyank N Gowda , Boyan Gao , Xiao Gu , Xiaobo Jin

Vision-Language Pre-training (VLP) has advanced the performance of many vision-language tasks, such as image-text retrieval, visual entailment, and visual reasoning. The pre-training mostly utilizes lexical databases and image queries in…

Computation and Language · Computer Science 2023-06-30 Yasmine Karoui , Rémi Lebret , Negar Foroutan , Karl Aberer

CLIP, one of the pioneering foundation models that connect images and text, has enabled many recent breakthroughs in computer vision. However, its associated training cost is prohibitively high, imposing a significant barrier to its…

Computer Vision and Pattern Recognition · Computer Science 2023-10-31 Xianhang Li , Zeyu Wang , Cihang Xie

Visual perceptual tasks aim to predict human judgment of images (e.g., emotions invoked by images, image quality assessment). Unlike objective tasks such as object/scene recognition, perceptual tasks rely on subjective human assessments,…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Amit Zalcher , Navve Wasserman , Roman Beliy , Oliver Heinimann , Michal Irani

Recently, large-scale pre-trained vision-language models (e.g. CLIP and ALIGN) have demonstrated remarkable effectiveness in acquiring transferable visual representations. To leverage the valuable knowledge encoded within these models for…

Computer Vision and Pattern Recognition · Computer Science 2023-08-28 Yi Zhang , Ce Zhang , Xueting Hu , Zhihai He

CLIP has demonstrated strong generalization in visual domains through natural language supervision, even for video action recognition. However, most existing approaches that adapt CLIP for action recognition have primarily focused on…

Computer Vision and Pattern Recognition · Computer Science 2026-04-27 Hyo Jin Jon , Longbin Jin , Eun Yi Kim

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,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Jingyun Wang , Guoliang Kang

Language-image pre-training is an effective technique for learning powerful representations in general domains. However, when directly turning to person representation learning, these general pre-training methods suffer from unsatisfactory…

Computer Vision and Pattern Recognition · Computer Science 2024-05-30 Jialong Zuo , Jiahao Hong , Feng Zhang , Changqian Yu , Hanyu Zhou , Changxin Gao , Nong Sang , Jingdong Wang

Contrastive Language-Image Pre-training (CLIP) has recently shown great promise in pixel-level zero-shot learning tasks. However, existing approaches utilizing CLIP's text and patch embeddings to generate semantic masks often misidentify…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Jingyao Li , Pengguang Chen , Shengju Qian , Shu Liu , Jiaya Jia

Contrastive vision-language models, such as CLIP, have demonstrated excellent zero-shot capability across semantic recognition tasks, mainly attributed to the training on a large-scale I&1T (one Image with one Text) dataset. This kind of…

Computer Vision and Pattern Recognition · Computer Science 2025-03-05 Zhichao Yang , Leida Li , Pengfei Chen , Jinjian Wu , Giuseppe Valenzise