Sort by: Year Popularity Relevance

Ensembles of Many Diverse Weak Defenses can be Strong: Defending Deep Neural Networks Against Adversarial Attacks

, , ,  - 2020

Despite achieving state-of-the-art performance across many domains, machine learning systems are highly vulnerable to subtle adversarial perturbations. Although defense approaches have been proposed in recent years, many have been bypassed by even weak adversarial attacks. An early study~\cite{he2017adversarial} shows that ensembles created by co...


A Nonparametric Off-Policy Policy Gradient

, , ,  - 2020

Reinforcement learning (RL) algorithms still suffer from high sample complexity despite outstanding recent successes. The need for intensive interactions with the environment is especially observed in many widely popular policy gradient algorithms that perform updates using on-policy samples. The price of such inefficiency becomes evident in real...


Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement

, , , , , ,  - 2020

The paper presents a novel method, Zero-Reference Deep Curve Estimation (Zero-DCE), which formulates light enhancement as a task of image-specific curve estimation with a deep network. Our method trains a lightweight deep network, DCE-Net, to estimate pixel-wise and high-order curves for dynamic range adjustment of a given image. The curve estima...


Torch-Struct: Deep Structured Prediction Library

 - 2020

The literature on structured prediction for NLP describes a rich collection of distributions and algorithms over sequences, segmentations, alignments, and trees; however, these algorithms are difficult to utilize in deep learning frameworks. We introduce Torch-Struct, a library for structured prediction designed to take advantage of and integrate...


AnomalyDAE: Dual autoencoder for anomaly detection on attributed networks

, ,  - 2020

Anomaly detection on attributed networks aims at finding nodes whose patterns deviate significantly from the majority of reference nodes, which is pervasive in many applications such as network intrusion detection and social spammer detection. However, most existing methods neglect the complex cross-modality interactions between network structure...


Domain-independent Extraction of Scientific Concepts from Research Articles

, , , ,  - 2020

We examine the novel task of domain-independent scientific concept extraction from abstracts of scholarly articles and present two contributions. First, we suggest a set of generic scientific concepts that have been identified in a systematic annotation process. This set of concepts is utilised to annotate a corpus of scientific abstracts from 10...


Unsupervised Any-to-Many Audiovisual Synthesis via Exemplar Autoencoders

, ,  - 2020

We present an unsupervised approach that enables us to convert the speech input of any one individual to an output set of potentially-infinitely many speakers. One can stand in front of a mic and be able to make their favorite celebrity say the same words. Our approach builds on simple autoencoders that project out-of-sample data to the distribut...


Deep Image Compression using Decoder Side Information

,  - 2020

We present a Deep Image Compression neural network that relies on side information, which is only available to the decoder. We base our algorithm on the assumption that the image available to the encoder and the image available to the decoder are correlated, and we let the network learn these correlations in the training phase. Then, at run tim...


Understanding the Automated Parameter Optimization on Transfer Learning for CPDP: An Empirical Study

, , , ,  - 2020

Data-driven defect prediction has become increasingly important in software engineering process. Since it is not uncommon that data from a software project is insufficient for training a reliable defect prediction model, transfer learning that borrows data/knowledge from other projects to facilitate the model building at the current project, name...


Universal Differential Equations for Scientific Machine Learning

, , , , , , ,  - 2020

In the context of science, the well-known adage "a picture is worth a thousand words" might well be "a model is worth a thousand datasets." Scientific models, such as Newtonian physics or biological gene regulatory networks, are human-driven simplifications of complex phenomena that serve as surrogates for the countless experiments that validated...