paper-with-me

홈 › Papers

WEmbSim: A Simple yet Effective Metric for Image Captioning

2020-12-24 · Naeha Sharif, Lyndon White, Mohammed Bennamoun, Wei Liu, Syed Afaq Ali Shah

The area of automatic image caption evaluation is still undergoing intensive research to address the needs of generating captions which can meet adequacy and fluency requirements. Based on our past attempts at developing highly sophisticated learning-based metrics, we have discovered that a simple cosine similarity measure using the Mean of Word Embeddings(MOWE) of captions can actually achieve a surprisingly high performance on unsupervised caption evaluation. This inspires our proposed work on an effective metric WEmbSim, which beats complex measures such as SPICE, CIDEr and WMD at system-level correlation with human judgments. Moreover, it also achieves the best accuracy at matching human consensus scores for caption pairs, against commonly used unsupervised methods. Therefore, we believe that WEmbSim sets a new baseline for any complex metric to be justified.

📄 PDF Abstract BibTeX arXiv:2012.13137

Code (0)

등록된 구현이 없습니다.

Tasks

Image CaptioningWord Embeddings

Similar Papers 제목 키워드 기반

Towards Unique and Informative Captioning of Images

2020-09-08 · ECCV 2020 8 · Zeyu Wang, Berthy Feng, Karthik Narasimhan, Olga Russakovsky

Despite considerable progress, state of the art image captioning models produce generic captions, leaving out important image details. Furthermore, these systems may even misrepresent the image in order to produce a simp…

DiversityImage CaptioningRe-Ranking

A Frustratingly Simple Approach for End-to-End Image Captioning

2022-01-30 · Ziyang Luo, Yadong Xi, Rongsheng Zhang, Jing Ma

Image Captioning is a fundamental task to join vision and language, concerning about cross-modal understanding and text generation. Recent years witness the emerging attention on image captioning. Most of existing works …

DecoderImage CaptioningObjectText Generation

Measuring directional bias amplification in image captions using predictability

2025-03-10 · Rahul Nair, Bhanu Tokas, Neel Shah, Hannah Kerner

When we train models on biased ML datasets, they not only learn these biases but can inflate them at test time - a phenomenon called bias amplification. To measure bias amplification in ML datasets, many co-occurrence-ba…

Image Captioningimage-classificationImage Classification

Distinctive Image Captioning via CLIP Guided Group Optimization

2022-08-08 · Youyuan Zhang, Jiuniu Wang, Hao Wu, Wenjia Xu

Image captioning models are usually trained according to human annotated ground-truth captions, which could generate accurate but generic captions. In this paper, we focus on generating distinctive captions that can dist…

Image Captioning

Actor-Critic Sequence Training for Image Captioning

2017-06-29 · Li Zhang, Flood Sung, Feng Liu, Tao Xiang 외

Generating natural language descriptions of images is an important capability for a robot or other visual-intelligence driven AI agent that may need to communicate with human users about what it is seeing. Such image cap…

AI AgentImage Captioningreinforcement-learningReinforcement Learning+1