Deliberation Learning for Image-to-Image Translation

Authors: Tianyu He, Yingce Xia, Jianxin Lin, Xu Tan, Di He, Tao Qin, Zhibo Chen

IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We verify our proposed method on four two-domain translation tasks and one multi-domain translation task. Both the qualitative and quantitative results demonstrate the effectiveness of our method.
Researcher Affiliation Collaboration 1CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, University of Science and Technology of China 2Microsoft Research Asia 3Key Laboratory of Machine Perception, MOE, School of EECS, Peking University
Pseudocode No The paper describes the framework with equations and textual steps for the training process but does not include any clearly labeled pseudocode or algorithm blocks.
Open Source Code No The paper mentions implementing based on official CycleGAN and StarGAN code (with corresponding footnotes pointing to their GitHub repositories), but does not explicitly state that *their* deliberation learning code is open-source or provide a link for it.
Open Datasets Yes Tasks. We select four tasks evaluated in Cycle GAN [Zhu et al., 2017]: semantic Label Photo translation on Cityscapes dataset [Cordts et al., 2016], Apple Orange translation, Winter Summer translation, and Photo Paint translation. We used the publicly available Celeb A dataset [Liu et al., 2015] for facial attributes translation.
Dataset Splits No The paper states for CelebA that 'The test set is randomly sampled (2, 000 images) and the remaining images are used for training.', but does not explicitly provide details about a validation set split for any of the datasets used.
Hardware Specification No The paper does not provide any specific hardware details such as GPU models, CPU types, or memory used for running the experiments.
Software Dependencies No The paper mentions using PyTorch for implementation but does not specify the version number or any other software dependencies with their respective versions.
Experiment Setup Yes Implementation details. We use Adam with initial learning rate 2 10 4 to train the models for the first 100 epochs. Then we linearly decay the learning rate to 0 in the next 100 epochs. For multi-domain, We use Adam with initial learning rate 1 10 4 to train the models for the first 100, 000 iterations. Then we linearly decay the learning rate to 0 in the next 100, 000 iterations. The batch size is set to 16.