Self-Supervised Sketch-to-Image Synthesis

Authors: Bingchen Liu, Yizhe Zhu, Kunpeng Song, Ahmed Elgammal2073-2081

AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on 10242 resolution demonstrate a new state-of-art-art performance of the proposed model on Celeb A-HQ and Wiki-Art datasets.
Researcher Affiliation Collaboration 1 Playform Artrendex Inc., USA 2 Department of Computer Science, Rutgers University
Pseudocode No The paper describes methods through text, equations, and diagrams, but does not include structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide an explicit statement about releasing source code or a link to a code repository for their method.
Open Datasets Yes We evaluate our model on two datasets, Celeb AHQ (Liu et al. 2015; Lee et al. 2020a) and Wiki Art 1. 1https://www.wikiart.org/
Dataset Splits No The paper specifies training and testing splits ('test on the rest images') but does not explicitly mention a separate validation split or its size/proportion.
Hardware Specification Yes The whole training process takes only 20 minutes on one RTX-2080 GPU.
Software Dependencies No The paper does not provide specific software dependencies with version numbers.
Experiment Setup Yes Ls tri = max(cos(f t s, f org s ) cos(f t s, f neg s ) + α, 0), where α is the margin. Lc tri = max(d(f t c, f pos c ) d(f t c, f neg c ) + β, 0), where d(, ) is the mean-squared distance, β is the margin. λ is the weight for the reconstruction term which we set to 10 for all datasets.