Search Results for author:
Found 27 papers, 13 papers with code
Calibrating Bayesian UNet++ for Sub-Seasonal Forecasting
Seasonal forecasting is a crucial task when it comes to detecting the extreme heat and colds that occur due to climate change.
epsilon-Mesh Attack: A Surface-based Adversarial Point Cloud Attack for Facial Expression Recognition
Due to the wide application area of point clouds and the recent advancements in deep neural networks, studies focusing on robust classification of the 3D point cloud data emerged.
PCLD: Point Cloud Layerwise Diffusion for Adversarial Purification
A typical way to assess a model's robustness is through adversarial attacks, where test-time examples are generated based on gradients to deceive the model.
EdVAE: Mitigating Codebook Collapse with Evidential Discrete Variational Autoencoders
We evidentially monitor the significance of attaining the probability distribution over the codebook embeddings, in contrast to softmax usage.
ProtoDiffusion: Classifier-Free Diffusion Guidance with Prototype Learning
Diffusion models are generative models that have shown significant advantages compared to other generative models in terms of higher generation quality and more stable training.
Textile Pattern Generation Using Diffusion Models
The fine-tuned diffusion model is trained with this newly created dataset, and its results are compared with the baseline models visually and numerically.
GaussianMLR: Learning Implicit Class Significance via Calibrated Multi-Label Ranking
We show that our method is able to accurately learn a representation of the incorporated positive rank order, which is not only consistent with the ground truth but also proportional to the underlying information.
Climate Model Driven Seasonal Forecasting Approach with Deep Learning
Three different setups (CMIP6; CMIP6 + elevation; CMIP6 + elevation + ERA5 finetuning) were used with both UNet and UNet++ algorithms resulting in six different models.
RLSEP: Learning Label Ranks for Multi-label Classification
Multi-label ranking maps instances to a ranked set of predicted labels from multiple possible classes.
Symmetry and Variance: Generative Parametric Modelling of Historical Brick Wall Patterns
This study integrates artificial intelligence and computational design tools to extract information from architectural heritage.
How to Combine Variational Bayesian Networks in Federated Learning
Federated Learning enables multiple data centers to train a central model collaboratively without exposing any confidential data.
Continual Learning of Multi-modal Dynamics with External Memory
We study the problem of fitting a model to a dynamical environment when new modes of behavior emerge sequentially.
Detecting Visual Design Principles in Art and Architecture through Deep Convolutional Neural Networks
Visual design is associated with the use of some basic design elements and principles.
Uncertainty-Based Dynamic Graph Neighborhoods For Medical Segmentation
However, there are two drawbacks of the approach: most of the edges in the graph are assigned randomly and the GCN is trained independently from the segmentation network.
Evidential Turing Processes
A probabilistic classifier with reliable predictive uncertainties i) fits successfully to the target domain data, ii) provides calibrated class probabilities in difficult regions of the target domain (e. g.\ class overlap), and iii) accurately identifies queries coming out of the target domain and rejects them.
Single Image Depth Estimation: An Overview
We review solutions to the problem of depth estimation, arguably the most important subtask in scene understanding.
ODFNet: Using orientation distribution functions to characterize 3D point clouds
Learning new representations of 3D point clouds is an active research area in 3D vision, as the order-invariant point cloud structure still presents challenges to the design of neural network architectures.
Ranked #18 on
3D Part Segmentation
on ShapeNet-Part
Exploring DeshuffleGANs in Self-Supervised Generative Adversarial Networks
Lastly, we show the contribution of the self-supervision tasks to the GAN training on the loss landscape and present that the effects of these tasks may not be cooperative to the adversarial training in some settings.
Relative Depth Estimation as a Ranking Problem
To this end, we have introduced a listwise ranking loss borrowed from ranking literature, weighted ListMLE, to the relative depth estimation problem.
A New Distributional Ranking Loss With Uncertainty: Illustrated in Relative Depth Estimation
We propose a new approach for the problem of relative depth estimation from a single image.
EfficientSeg: An Efficient Semantic Segmentation Network
Deep neural network training without pre-trained weights and few data is shown to need more training iterations.
Ranked #1 on
Semantic Segmentation
on Cityscapes VIPriors subset
Rethinking CNN-Based Pansharpening: Guided Colorization of Panchromatic Images via GANs
Convolutional Neural Networks (CNN)-based approaches have shown promising results in pansharpening of satellite images in recent years.
DeshuffleGAN: A Self-Supervised GAN to Improve Structure Learning
Generative Adversarial Networks (GANs) triggered an increased interest in problem of image generation due to their improved output image quality and versatility for expansion towards new methods.
Medical Imaging with Deep Learning: MIDL 2019 -- Extended Abstract Track
This compendium gathers all the accepted extended abstracts from the Second International Conference on Medical Imaging with Deep Learning (MIDL 2019), held in London, UK, 8-10 July 2019.
Generative Adversarial Training for MRA Image Synthesis Using Multi-Contrast MRI
To that end, we incorporate steerable filter responses of the generated and reference images inside a Huber function loss term.
Patch-Based Image Inpainting with Generative Adversarial Networks
Area of image inpainting over relatively large missing regions recently advanced substantially through adaptation of dedicated deep neural networks.
Deep Stacked Networks with Residual Polishing for Image Inpainting
Then the second network modifies the repaired image to cancel the noise introduced by the first network.
