Search Results for author:
Found 6 papers, 2 papers with code
Towards Architecture-Agnostic Untrained Network Priors for Image Reconstruction with Frequency Regularization
We show that even with just one extra line of code, the overfitting issues in underperforming architectures can be alleviated such that their performance gaps with the high-performing counterparts can be largely closed despite their distinct configurations, mitigating the need for architecture tuning.
The Devil is in the Upsampling: Architectural Decisions Made Simpler for Denoising with Deep Image Prior
Existing methods mostly handcraft or search for the architecture from a large design space, due to the lack of understanding on how the architectural choice corresponds to the image.
Encouraging Disentangled and Convex Representation with Controllable Interpolation Regularization
(2) They lack convexity constraints, which is important for meaningfully manipulating specific attributes for downstream tasks.
Graph Autoencoder for Graph Compression and Representation Learning
We consider the problem of graph data compression and representation.
Generative Auto-Encoder: Non-adversarial Controllable Synthesis with Disentangled Exploration
DEAE can become a generative model and synthesis semantic controllable samples by interpolating latent code, which can even synthesis novel attribute value never is shown in the original dataset.
Sketch-Inspector: a Deep Mixture Model for High-Quality Sketch Generation of Cats
Based on that, a sketch generating system with an assistant convolutional neural network (CNN) predictor to suggest the shape of the next stroke is presented in this paper.
