Image Manipulation via Multi-Hop Instructions - A New Dataset and Weakly-Supervised Neuro-Symbolic Approach

Harman Singh, Poorva Garg, Mohit Gupta, Kevin Shah, Ashish Goswami, Satyam Modi, Arnab Mondal, Dinesh Khandelwal, Dinesh Garg, Parag Singla


Abstract
We are interested in image manipulation via natural language text – a task that is useful for multiple AI applications but requires complex reasoning over multi-modal spaces. We extend recently proposed Neuro Symbolic Concept Learning (NSCL), which has been quite effective for the task of Visual Question Answering (VQA), for the task of image manipulation. Our system referred to as NeuroSIM can perform complex multi-hop reasoning over multi-object scenes and only requires weak supervision in the form of annotated data for VQA. NeuroSIM parses an instruction into a symbolic program, based on a Domain Specific Language (DSL) comprising of object attributes and manipulation operations, that guides its execution. We create a new dataset for the task, and extensive experiments demonstrate that NeuroSIM is highly competitive with or beats SOTA baselines that make use of supervised data for manipulation.
Anthology ID:
2023.emnlp-main.181
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2975–3007
Language:
URL:
https://aclanthology.org/2023.emnlp-main.181
DOI:
10.18653/v1/2023.emnlp-main.181
Bibkey:
Cite (ACL):
Harman Singh, Poorva Garg, Mohit Gupta, Kevin Shah, Ashish Goswami, Satyam Modi, Arnab Mondal, Dinesh Khandelwal, Dinesh Garg, and Parag Singla. 2023. Image Manipulation via Multi-Hop Instructions - A New Dataset and Weakly-Supervised Neuro-Symbolic Approach. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 2975–3007, Singapore. Association for Computational Linguistics.
Cite (Informal):
Image Manipulation via Multi-Hop Instructions - A New Dataset and Weakly-Supervised Neuro-Symbolic Approach (Singh et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.181.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.181.mp4