SSCR: Iterative Language-Based Image Editing via Self-Supervised Counterfactual Reasoning

Tsu-Jui Fu, Xin Wang, Scott Grafton, Miguel Eckstein, William Yang Wang


Abstract
Iterative Language-Based Image Editing (ILBIE) tasks follow iterative instructions to edit images step by step. Data scarcity is a significant issue for ILBIE as it is challenging to collect large-scale examples of images before and after instruction-based changes. Yet, humans still accomplish these editing tasks even when presented with an unfamiliar image-instruction pair. Such ability results from counterfactual thinking, the ability to think about possible alternatives to events that have happened already. In this paper, we introduce a Self-Supervised Counterfactual Reasoning (SSCR) framework that incorporates counterfactual thinking to overcome data scarcity. SSCR allows the model to consider out-of-distribution instructions paired with previous images. With the help of cross-task consistency (CTC), we train these counterfactual instructions in a self-supervised scenario. Extensive results show that SSCR improves the correctness of ILBIE in terms of both object identity and position, establishing a new state of the art (SOTA) on two IBLIE datasets (i-CLEVR and CoDraw). Even with only 50% of the training data, SSCR achieves a comparable result to using complete data.
Anthology ID:
2020.emnlp-main.357
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4413–4422
Language:
URL:
https://aclanthology.org/2020.emnlp-main.357
DOI:
10.18653/v1/2020.emnlp-main.357
Bibkey:
Cite (ACL):
Tsu-Jui Fu, Xin Wang, Scott Grafton, Miguel Eckstein, and William Yang Wang. 2020. SSCR: Iterative Language-Based Image Editing via Self-Supervised Counterfactual Reasoning. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4413–4422, Online. Association for Computational Linguistics.
Cite (Informal):
SSCR: Iterative Language-Based Image Editing via Self-Supervised Counterfactual Reasoning (Fu et al., EMNLP 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2020.emnlp-main.357.pdf
Video:
 https://slideslive.com/38939243
Code
 tsujuifu/pytorch_sscr