paper-with-me

Papers

Contrastive Learning for Image Captioning

2017-10-06 · NeurIPS 2017 12 · Bo Dai, Dahua Lin

Image captioning, a popular topic in computer vision, has achieved substantial progress in recent years. However, the distinctiveness of natural descriptions is often overlooked in previous work. It is closely related to the quality of captions, as distinctive captions are more likely to describe images with their unique aspects. In this work, we propose a new learning method, Contrastive Learning (CL), for image captioning. Specifically, via two constraints formulated on top of a reference model, the proposed method can encourage distinctiveness, while maintaining the overall quality of the generated captions. We tested our method on two challenging datasets, where it improves the baseline model by significant margins. We also showed in our studies that the proposed method is generic and can be used for models with various structures.

📄 PDF Abstract BibTeX arXiv:1710.02534

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningImage Captioning

Similar Papers 제목 키워드 기반

Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation

2023-03-21 · CVPR 2023 1 · Sara Sarto, Manuele Barraco, Marcella Cornia, Lorenzo Baraldi 외

The CLIP model has been recently proven to be very effective for a variety of cross-modal tasks, including the evaluation of captions generated from vision-and-language architectures. In this paper, we propose a new reci…

Contrastive LearningImage CaptioningVideo Captioning

Style-Aware Contrastive Learning for Multi-Style Image Captioning

2023-01-26 · Yucheng Zhou, Guodong Long

Existing multi-style image captioning methods show promising results in generating a caption with accurate visual content and desired linguistic style. However, existing methods overlook the relationship between linguist…

Contrastive LearningImage CaptioningRetrievalTriplet

Image Captioners Are Scalable Vision Learners Too

2023-06-13 · NeurIPS 2023 11 · Michael Tschannen, Manoj Kumar, Andreas Steiner, Xiaohua Zhai 외

Contrastive pretraining on image-text pairs from the web is one of the most popular large-scale pretraining strategies for vision backbones, especially in the context of large multimodal models. At the same time, image c…

DecoderImage Captioning

RCA-NOC: Relative Contrastive Alignment for Novel Object Captioning

2023-12-11 · ICCV 2023 1 · Jiashuo Fan, Yaoyuan Liang, Leyao Liu, ShaoLun Huang 외

In this paper, we introduce a novel approach to novel object captioning which employs relative contrastive learning to learn visual and semantic alignment. Our approach maximizes compatibility between regions and object …

Contrastive LearningObjectTAG

Context-Aware Group Captioning via Self-Attention and Contrastive Features

2020-04-07 · CVPR 2020 6 · Zhuowan Li, Quan Tran, Long Mai, Zhe Lin 외

While image captioning has progressed rapidly, existing works focus mainly on describing single images. In this paper, we introduce a new task, context-aware group captioning, which aims to describe a group of target ima…

Image Captioning