Then we introduce a semantic mapper that produces the proxy masks from various input conditions including semantic masks.

This process enables the value (feature maps) to be rearranged (through a weighted sum) to align with the form of the query, thereby reflecting their strong correspondence. The input noise is removed because its stochasticity slows down the training. Given the need for balancing between high correspondence and image quality, we empirically set the weights of our loss terms. To demonstrate the influence of the additional losses introduced in our method, we provide both quantitative and qualitative ablations in Figure S2 and S3, respectively. Nonetheless, caution is warranted when overly increasing the number of clusters.

Experiments demonstrate that our method outperforms state-of-the-art methods.

For image synthesis, we propose a finite perturbation approach to enhance the diversity of generated results without changing the semantic categories. Experiments show that our SemFlow achieves competitive results on semantic segmentation and semantic image synthesis tasks.

This process enables the value (feature maps) to be rearranged (through a weighted sum) to align with the form of the query, thereby reflecting their strong correspondence. The input noise is removed because its stochasticity slows down the training. Given the need for balancing between high correspondence and image quality, we empirically set the weights of our loss terms. To demonstrate the influence of the additional losses introduced in our method, we provide both quantitative and qualitative ablations in Figure S2 and S3, respectively. Nonetheless, caution is warranted when overly increasing the number of clusters.

Neural Information Processing Systems http://nips.cc/

This paper proposes a strongly conditional network for generating images from semantic maps. How impacted is this network by small changes in the input map - for example given 3 sequential frames of a video (as segmentation maps) - is the model consistent in assigning colors and structures? Or do small changes in the geometry of the semantic objects have a large impact on the output? This is mostly curiousity, as having smoothness inherent in the model has large potential for video applications. Some amount of qualitative results comparing to other models were shown, but showing the important regions of the input conditioning, and the influence of input perturbations on the model output could also lead to valuable insight - using something like GradCAM or related methods may be possible for checking the importance of input features.

All reviewers are in unanimous agreement for acceptance. The paper has a number of interesting contributions, mostly empirical, in utilizing a conditional weights network and feature pyramids. As promised in your rebuttal, please release code before acceptance.