English
Related papers

Related papers: Mining Fine-Grained Image-Text Alignment for Zero-…

200 papers

Contrastive Language-Image Pre-Training (CLIP) is a popular method for learning multimodal latent spaces with well-organized semantics. Despite its wide range of applications, CLIP's latent space is known to fail at handling complex…

Machine Learning · Computer Science 2026-03-17 Raphi Kang , Yue Song , Georgia Gkioxari , Pietro Perona

The advent of vision-language pre-training techniques enhanced substantial progress in the development of models for image captioning. However, these models frequently produce generic captions and may omit semantically important image…

Computer Vision and Pattern Recognition · Computer Science 2023-11-17 Noam Rotstein , David Bensaid , Shaked Brody , Roy Ganz , Ron Kimmel

Recent lightweight image captioning models using retrieved data mainly focus on text prompts. However, previous works only utilize the retrieved text as text prompts, and the visual information relies only on the CLIP visual embedding.…

Computer Vision and Pattern Recognition · Computer Science 2025-01-27 Taewhan Kim , Soeun Lee , Si-Woo Kim , Dong-Jin Kim

Image Difference Captioning (IDC) aims at generating sentences to describe differences between two similar-looking images. Conventional approaches learn an IDC model with a pre-trained and usually frozen visual feature extractor.…

Computer Vision and Pattern Recognition · Computer Science 2022-10-19 Zixin Guo , Tzu-Jui Julius Wang , Jorma Laaksonen

We present RECLIP (Resource-efficient CLIP), a simple method that minimizes computational resource footprint for CLIP (Contrastive Language Image Pretraining). Inspired by the notion of coarse-to-fine in computer vision, we leverage small…

Computer Vision and Pattern Recognition · Computer Science 2023-09-01 Runze Li , Dahun Kim , Bir Bhanu , Weicheng Kuo

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…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Yiming Zhang , Zhuokai Zhao , Zhaorun Chen , Zhili Feng , Zenghui Ding , Yining Sun

Traditional computer vision models are trained to predict a fixed set of predefined categories. Recently, natural language has been shown to be a broader and richer source of supervision that provides finer descriptions to visual concepts…

Computer Vision and Pattern Recognition · Computer Science 2021-04-20 Ruizhe Cheng , Bichen Wu , Peizhao Zhang , Peter Vajda , Joseph E. Gonzalez

Contrastive Language-Image Pre-training (CLIP) is an approach that has advanced research and applications in computer vision, fueling modern recognition systems and generative models. We believe that the main ingredient to the success of…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Hu Xu , Saining Xie , Xiaoqing Ellen Tan , Po-Yao Huang , Russell Howes , Vasu Sharma , Shang-Wen Li , Gargi Ghosh , Luke Zettlemoyer , Christoph Feichtenhofer

Contrastive vision-language models, such as CLIP, have garnered considerable attention for various downstream tasks, mainly due to the remarkable ability of the learned features for generalization. However, the features they learned often…

Computer Vision and Pattern Recognition · Computer Science 2025-04-24 Yichao Cai , Yuhang Liu , Zhen Zhang , Javen Qinfeng Shi

The conventional training approach for image captioning involves pre-training a network using teacher forcing and subsequent fine-tuning with Self-Critical Sequence Training to maximize hand-crafted captioning metrics. However, when…

Computer Vision and Pattern Recognition · Computer Science 2024-08-28 Nicholas Moratelli , Davide Caffagni , Marcella Cornia , Lorenzo Baraldi , Rita Cucchiara

Dense video captioning, a task of localizing meaningful moments and generating relevant captions for videos, often requires a large, expensive corpus of annotated video segments paired with text. In an effort to minimize the annotation…

Computer Vision and Pattern Recognition · Computer Science 2023-07-13 Yongrae Jo , Seongyun Lee , Aiden SJ Lee , Hyunji Lee , Hanseok Oh , Minjoon Seo

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…

Computer Vision and Pattern Recognition · Computer Science 2022-07-18 Shibani Santurkar , Yann Dubois , Rohan Taori , Percy Liang , Tatsunori Hashimoto

Contrastive Vision-Language Pre-training(CLIP) demonstrates impressive zero-shot capability. The key to improve the adaptation of CLIP to downstream task with few exemplars lies in how to effectively model and transfer the useful knowledge…

Computer Vision and Pattern Recognition · Computer Science 2024-07-01 Cilin Yan , Haochen Wang , Xiaolong Jiang , Yao Hu , Xu Tang , Guoliang Kang , Efstratios Gavves

Large pre-trained vision-language models like CLIP have shown great potential in learning representations that are transferable across a wide range of downstream tasks. Different from the traditional representation learning that is based…

Computer Vision and Pattern Recognition · Computer Science 2022-10-07 Kaiyang Zhou , Jingkang Yang , Chen Change Loy , Ziwei Liu

Existing contrastive language-image pre-training aims to learn a joint representation by matching abundant image-text pairs. However, the number of image-text pairs in medical datasets is usually orders of magnitude smaller than that in…

Computer Vision and Pattern Recognition · Computer Science 2024-01-04 Jiarun Liu , Hong-Yu Zhou , Cheng Li , Weijian Huang , Hao Yang , Yong Liang , Shanshan Wang

Open-vocabulary semantic segmentation aims to assign semantic labels to each pixel without being constrained by a predefined set of categories. While Contrastive Language-Image Pre-training (CLIP) excels in zero-shot classification, it…

Computer Vision and Pattern Recognition · Computer Science 2025-08-04 Dengke Zhang , Fagui Liu , Quan Tang

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)…

Computer Vision and Pattern Recognition · Computer Science 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

Supervised image captioning approaches have made great progress, but it is challenging to collect high-quality human-annotated image-text data. Recently, large-scale vision and language models (e.g., CLIP) and large-scale generative…

Computer Vision and Pattern Recognition · Computer Science 2024-03-29 Yiyu Wang , Hao Luo , Jungang Xu , Yingfei Sun , Fan Wang

Recent advances in vision-language foundational models, such as CLIP, have demonstrated significant strides in zero-shot classification. However, the extensive parameterization of models like CLIP necessitates a resource-intensive…

Computer Vision and Pattern Recognition · Computer Science 2024-11-08 Qijie Wang , Guandu Liu , Bin Wang

We propose a weakly supervised approach for creating maps using free-form textual descriptions. We refer to this work of creating textual maps as zero-shot mapping. Prior works have approached mapping tasks by developing models that predict…

Computer Vision and Pattern Recognition · Computer Science 2024-04-15 Aayush Dhakal , Adeel Ahmad , Subash Khanal , Srikumar Sastry , Hannah Kerner , Nathan Jacobs