Learning Hierarchical Semantic Image Manipulation through Structured Representations
Authors: Seunghoon Hong, Xinchen Yan, Thomas S. Huang, Honglak Lee
NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental evaluations demonstrate the advantages of the hierarchical manipulation framework over existing image generation and context hole-filing models, both qualitatively and quantitatively. We conduct both quantitative and qualitative evaluations on the Cityscape dataset [4], a semantic understanding benchmark of European urban street scenes containing 5,000 high-resolution images with fine-grained annotations including instance-wise map and semantic map from 30 categories. |
| Researcher Affiliation | Collaboration | University of Michigan Google Brain {hongseu,xcyan,thomaseh,honglak}@umich.edu honglak@google.com |
| Pseudocode | No | The paper includes architectural diagrams (Figure 1, Figure 2, Figure 3) and mathematical equations for loss functions and model components, but it does not present any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper states: "Our Py Torch implementation will be open-sourced." This is a promise of future release, not concrete access to the code at the time of publication. |
| Open Datasets | Yes | We conduct both quantitative and qualitative evaluations on the Cityscape dataset [4], a semantic understanding benchmark of European urban street scenes containing 5,000 high-resolution images with fine-grained annotations including instance-wise map and semantic map from 30 categories. To further demonstrate the image manipulation results on more complex scene, we also conduct qualitative experiments on bedroom images from ADE20K dataset [31]. |
| Dataset Splits | Yes | For evaluation, we measure the generation performance on each of the foreground object bounding box in 500 validation images. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware used for running the experiments, such as GPU models, CPU types, or memory specifications. |
| Software Dependencies | No | The paper mentions "Our Py Torch implementation will be open-sourced," indicating the use of PyTorch, but it does not specify any version numbers for PyTorch or any other software dependencies crucial for replication. |
| Experiment Setup | Yes | For training, we employ an Adam optimizer [12] with learning rate 0.0002, β1 = 0.5, β2 = 0.999 and linearly decrease the learning rate after the first 100-epochs for training. The hyper-parameters λobj, λctx, λfeature are set to 10. |