Latest Research
Classifying the classifier: dissecting the weight space of neural networks
of neural network classifiers, and train a large number of models to represent the weight space.
Ensemble neural network forecasts with singular value decomposition
Random perturbations of the initial model state typically provide unsatisfactory results when applied to numerical weather prediction models.
Geom-GCN: Geometric Graph Convolutional Networks
• graphdml-uiuc-jlu/geom-gcn
• 
From the observations on classical neural network and network geometry, we propose a novel geometric aggregation scheme for graph neural networks to overcome the two weaknesses.
End-to-end semantic segmentation of personalized deep brain structures for non-invasive brain stimulation
However, it is difficult to determine the amount and distribution of the electric field (EF) in the different brain regions due to anatomical complexity and high inter-subject variability.
PACOH: Bayes-Optimal Meta-Learning with PAC-Guarantees
• jonasrothfuss/meta_learning_pacoh
•
Meta-learning can successfully acquire useful inductive biases from data, especially when a large number of meta-tasks are available.
EndoL2H: Deep Super-Resolution for Capsule Endoscopy
• akgokce/EndoL2H
•
Enhanced-resolution endoscopy has shown to improve adenoma detection rate for conventional endoscopy and is likely to do the same for capsule endoscopy.
A Framework for End-to-End Learning on Semantic Tree-Structured Data
In this paper, we propose a novel framework for end-to-end learning on generic semantic tree-structured data of arbitrary topology and heterogeneous data types, such as data expressed in JSON, XML and so on.
GANILLA: Generative Adversarial Networks for Image to Illustration Translation
To address this problem, we propose a new framework for the quantitative evaluation of image-to-illustration models, where both content and style are taken into account using separate classifiers.
Learning Cross-modal Context Graph for Visual Grounding
AAAI-2020 2020
• youngfly11/LCMCG-PyTorch
•
To address their limitations, this paper proposes a language-guided graph representation to capture the global context of grounding entities and their relations, and develop a cross-modal graph matching strategy for the multiple-phrase visual grounding task.
GRAPH MATCHING LANGUAGE MODELLING NATURAL LANGUAGE VISUAL GROUNDING PHRASE GROUNDING
Automatically Discovering and Learning New Visual Categories with Ranking Statistics
ICLR 2020 2020
• k-han/AutoNovel
•
In this work we address this problem by combining three ideas: (1) we suggest that the common approach of bootstrapping an image representation using the labeled data only introduces an unwanted bias, and that this can be avoided by using self-supervised learning to train the representation from scratch on the union of labelled and unlabelled data; (2) we use rank statistics to transfer the model's knowledge of the labelled classes to the problem of clustering the unlabelled images; and, (3) we train the data representation by optimizing a joint objective function on the labelled and unlabelled subsets of the data, improving both the supervised classification of the labelled data, and the clustering of the unlabelled data.