paper-with-me

Papers

Exploring Diverse In-Context Configurations for Image Captioning

2023-05-24 · NeurIPS 2023 11 · Xu Yang, Yongliang Wu, Mingzhuo Yang, Haokun Chen, Xin Geng

After discovering that Language Models (LMs) can be good in-context few-shot learners, numerous strategies have been proposed to optimize in-context sequence configurations. Recently, researchers in Vision-Language (VL) domains also develop their few-shot learners, while they only use the simplest way, ie., randomly sampling, to configure in-context image-text pairs. In order to explore the effects of varying configurations on VL in-context learning, we devised four strategies for image selection and four for caption assignment to configure in-context image-text pairs for image captioning. Here Image Captioning is used as the case study since it can be seen as the visually-conditioned LM. Our comprehensive experiments yield two counter-intuitive but valuable insights, highlighting the distinct characteristics of VL in-context learning due to multi-modal synergy, as compared to the NLP case. Furthermore, in our exploration of optimal combination strategies, we observed an average performance enhancement of 20.9 of CIDEr scores compared to the baseline. The code is given in https://github.com/yongliang-wu/ExploreCfg.

📄 PDF Abstract BibTeX arXiv:2305.14800

Code (1)

yongliang-wu/explorecfg 공식 구현 pytorch

Tasks

Image CaptioningIn-Context Learning

Similar Papers 제목 키워드 기반

C3-Bench: A Context-Aware Change Captioning Benchmark

2026-06-24 · Jae-Woo Kim, Hyeongbeom Kim, Ue-Hwan Kim arxiv

While Change Captioning systems have garnered substantial attention to respond to our evolving world, their true performance on diverse real-world change contexts remains largely unexplored due to the lack of comprehensi…

Image Editing

Activitynet 2019 Task 3: Exploring Contexts for Dense Captioning Events in Videos

2019-07-11 · Shizhe Chen, Yuqing Song, Yida Zhao, Qin Jin 외

Contextual reasoning is essential to understand events in long untrimmed videos. In this work, we systematically explore different captioning models with various contexts for the dense-captioning events in video task, wh…

Dense CaptioningDense Video CaptioningDiversityVideo Captioning

Exploring and Distilling Cross-Modal Information for Image Captioning

2020-02-28 · Fenglin Liu, Xuancheng Ren, Yuanxin Liu, Kai Lei 외

Recently, attention-based encoder-decoder models have been used extensively in image captioning. Yet there is still great difficulty for the current methods to achieve deep image understanding. In this work, we argue tha…

AttributeDecoderImage Captioning

Diverse Image Captioning with Context-Object Split Latent Spaces

2020-11-02 · NeurIPS 2020 12 · Shweta Mahajan, Stefan Roth

Diverse image captioning models aim to learn one-to-many mappings that are innate to cross-domain datasets, such as of images and texts. Current methods for this task are based on generative latent variable models, e.g. …

DiversityImage CaptioningObject

Dual Graph Convolutional Networks with Transformer and Curriculum Learning for Image Captioning

2021-08-05 · Xinzhi Dong, Chengjiang Long, Wenju Xu, Chunxia Xiao

Existing image captioning methods just focus on understanding the relationship between objects or instances in a single image, without exploring the contextual correlation existed among contextual image. In this paper, w…

Image CaptioningObject