Deep Learning
MetaReg: Towards Domain Generalization using Meta-Regularization
Yogesh Balaji, Swami Sankaranarayanan, Rama Chellappa
Existing machine learning algorithms including deep neural networks achieve good performance in cases where the training and the test data are sampled from the same distribution. While this is a reasonable assumption to make, it might not hold true in practice.
Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning
Tom Zahavy, Matan Haroush, Nadav Merlis, Daniel J. Mankowitz, Shie Mannor
Action Elimination Network (AEN) that eliminates sub-optimal actions.
Evolutionary Stochastic Gradient Descent for Optimization of Deep Neural Networks
Xiaodong Cui, Wei Zhang, Zoltán Tüske, Michael Picheny
The complementarity between SGD and EA is worth investigating.
Neural Proximal Gradient Descent for Compressive Imaging
Morteza Mardani, Qingyun Sun, David Donoho, Vardan Papyan, Hatef Monajemi, Shreyas Vasanawala, John Pauly
Neural Information Processing Systems http://nips.cc/
Learning Hierarchical Semantic Image Manipulation through Structured Representations
Seunghoon Hong, Xinchen Yan, Thomas S. Huang, Honglak Lee
Then our image generator fills in the pixel-level textures guided by the semantic layout. Such framework allows a user to manipulate images at object-level by adding, removing, and moving one bounding box at a time. Experimental evaluations demonstrate the advantages of the hierarchical manipulation framework over existing image generation and context hole-filing models, both qualitatively and quantitatively.
An intriguing failing of convolutional neural networks and the CoordConv solution
Rosanne Liu, Joel Lehman, Piero Molino, Felipe Petroski Such, Eric Frank, Alex Sergeev, Jason Yosinski
Neural Information Processing Systems http://nips.cc/
Joint Sub-bands Learning with Clique Structures for Wavelet Domain Super-Resolution
Zhisheng Zhong, Tiancheng Shen, Yibo Yang, Zhouchen Lin, Chao Zhang
Convolutional neural networks (CNNs) have recently achieved great success in single-image super-resolution (SISR). However, these methods tend to produce over-smoothed outputs and miss some textural details.
Deep Anomaly Detection Using Geometric Transformations
Given a sample of images, all known to belong to a "normal"
Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding
Kexin Yi, Jiajun Wu, Chuang Gan, Antonio Torralba, Pushmeet Kohli, Josh Tenenbaum
Second, the model is more data-and memory-efficient: it performs well after learning on a small number of training data; it can also encode an image into a compact representation, requiring less storage than existing methods for offline question answering.
Deep State Space Models for Time Series Forecasting
We present a novel approach to probabilistic time series forecasting that combines state space models with deep learning. By parametrizing a per-time-series linear state space model with a jointly-learned recurrent neural network, our method retains desired properties of state space models such as data efficiency and inter-pretability, while making use of the ability to learn complex patterns from raw data offered by deep learning approaches. Our method scales gracefully from regimes where little training data is available to regimes where data from large collection of time series can be leveraged to learn accurate models. We provide qualitative as well as quantitative results with the proposed method, showing that it compares favorably to the state-of-the-art.