Editing an image automatically via a linguistic request can significantly save laborious manual work and is friendly to photography novice. In this paper, we focus on the task of language-guided global image editing. Existing works suffer from imbalanced and insufficient data distribution of real-world datasets and thus fail to understand language requests well. To handle this issue, we propose to create a cycle with our image generator by creating a novel model called Editing Description Network (EDNet) which predicts an editing embedding given a pair of images. Given the cycle, we propose several free augmentation strategies to help our model understand various editing requests given the imbalanced dataset. In addition, two other novel ideas are proposed: an Image-Request Attention (IRA) module which allows our method to edit an image spatial-adaptively when the image requires different editing degree at different regions, as well as a new evaluation metric for this task which is more semantic and reasonable than conventional pixel losses (e.g. L1). Extensive experiments on two benchmark datasets demonstrate the effectiveness of our method over existing approaches.

Varieties of topological quasi-Boolean algebras in the vicinity of pre-rough algebras [28, 29] are expanded to residuated algebraic structures by introducing a new implication operation and its residual in these structures. Sequent calculi for some classes of residuated algebraic structures are established. These sequent calculi have the strong finite model property which yields the decidability of the word problem for corresponding classes of algebraic structures.