Kayser, Maxime;
Camburu, Oana-Maria;
Salewski, Leonard;
Emde, Cornelius;
Do, Virginie;
Akata, Zeynep;
Lukasiewicz, Thomas;
(2022)
e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks.
In:
2021 IEEE/CVF International Conference on Computer Vision (ICCV).
(pp. pp. 1224-1234).
IEEE: Montreal, QC, Canada.
Preview |
Text
Camburu_evil.pdf Download (716kB) | Preview |
Abstract
Recently, there has been an increasing number of efforts to introduce models capable of generating natural language explanations (NLEs) for their predictions on vision-language (VL) tasks. Such models are appealing, because they can provide human-friendly and comprehensive explanations. However, there is a lack of comparison between existing methods, which is due to a lack of re-usable evaluation frameworks and a scarcity of datasets. In this work, we introduce e-ViL and e-SNLI-VE. e-ViL is a benchmark for explainable vision-language tasks that establishes a unified evaluation framework and provides the first comprehensive comparison of existing approaches that generate NLEs for VL tasks. It spans four models and three datasets and both automatic metrics and human evaluation are used to assess model-generated explanations. e-SNLI-VE is currently the largest existing VL dataset with NLEs (over 430k instances). We also propose a new model that combines UNITER [15], which learns joint embeddings of images and text, and GPT-2 [38], a pre-trained language model that is well-suited for text generation. It surpasses the previous state of the art by a large margin across all datasets. Code and data are available here: https://github.com/maximek3/e-ViL.
| Type: | Proceedings paper |
|---|---|
| Title: | e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks |
| Event: | 2021 IEEE/CVF International Conference on Computer Vision (ICCV) |
| Dates: | 10 Oct 2021 - 17 Oct 2021 |
| ISBN-13: | 978-1-6654-2812-5 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1109/iccv48922.2021.00128 |
| Publisher version: | http://dx.doi.org/10.1109/iccv48922.2021.00128 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | Explainable AI; Datasets and evaluation; Vision + language |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10184046 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
