SSCR: Iterative Language-Based Image Editing via Self-Supervised Counterfactual Reasoning
This work addresses data scarcity for iterative language-based image editing, an incremental improvement in a domain-specific task.
The paper tackles the data scarcity problem in iterative language-based image editing by introducing a self-supervised counterfactual reasoning framework, which improves correctness in object identity and position, achieving state-of-the-art results on two datasets and comparable performance with only 50% of training data.
Iterative Language-Based Image Editing (IL-BIE) 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. However, humans still accomplish these editing tasks even when presented with an unfamiliar image-instruction pair. Such ability results from counterfactual thinking and the ability to think about 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.