590 citations · 2.3k across the 19 of their papers we have counts for
19 papers
What Are You Doing? A Closer Look at Controllable Human Video Generation
Emanuele Bugliarello, Anurag Arnab, Roni Paiss +3
High-quality benchmarks are crucial for driving progress in machine learning research. However, despite the growing interest in video generation, there is no comprehensive dataset…
StoryBench: A Multifaceted Benchmark for Continuous Story Visualization
Emanuele Bugliarello, Hernan Moraldo, Ruben Villegas +7
Generating video stories from text prompts is a complex task. In addition to having high visual quality, videos need to realistically adhere to a sequence of text prompts whilst be…
Phenaki: Variable Length Video Generation From Open Domain Textual Description
Ruben Villegas, Mohammad Babaeizadeh, Pieter-Jan Kindermans +6
We present Phenaki, a model capable of realistic video synthesis, given a sequence of textual prompts. Generating videos from text is particularly challenging due to the computatio…
When adversarial examples are excusable
Pieter-Jan Kindermans, Charles Staats
Neural networks work remarkably well in practice and theoretically they can be universal approximators. However, they still make mistakes and a specific type of them called adversa…
TabNAS: Rejection Sampling for Neural Architecture Search on Tabular Datasets
Chengrun Yang, Gabriel Bender, Hanxiao Liu +5
The best neural architecture for a given machine learning problem depends on many factors: not only the complexity and structure of the dataset, but also on resource constraints in…
Can weight sharing outperform random architecture search? An investigation with TuNAS
Gabriel Bender, Hanxiao Liu, Bo Chen +4
Efficient Neural Architecture Search methods based on weight sharing have shown good promise in democratizing Neural Architecture Search for computer vision models. There is, howev…
Discovering Multi-Hardware Mobile Models via Architecture Search
Grace Chu, Okan Arikan, Gabriel Bender +7
Hardware-aware neural architecture designs have been predominantly focusing on optimizing model performance on single hardware and model development complexity, where another impor…
MobileDets: Searching for Object Detection Architectures for Mobile Accelerators
Yunyang Xiong, Hanxiao Liu, Suyog Gupta +7
Inverted bottleneck layers, which are built upon depthwise convolutions, have been the predominant building blocks in state-of-the-art object detection models on mobile devices. In…
BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models
Jiahui Yu, Pengchong Jin, Hanxiao Liu +7
Neural architecture search (NAS) has shown promising results discovering models that are both accurate and fast. For NAS, training a one-shot model has become a popular strategy to…
Neural Predictor for Neural Architecture Search
Wei Wen, Hanxiao Liu, Hai Li +3
Neural Architecture Search methods are effective but often use complex algorithms to come up with the best architecture. We propose an approach with three basic steps that is conce…
iNNvestigate neural networks!
Maximilian Alber, Sebastian Lapuschkin, Philipp Seegerer +7
In recent years, deep neural networks have revolutionized many application domains of machine learning and are key components of many critical decision or predictive processes. The…
Backprop Evolution
Maximilian Alber, Irwan Bello, Barret Zoph +3
The back-propagation algorithm is the cornerstone of deep learning. Despite its importance, few variations of the algorithm have been attempted. This work presents an approach to d…
A Benchmark for Interpretability Methods in Deep Neural Networks
Sara Hooker, Dumitru Erhan, Pieter-Jan Kindermans +1
We propose an empirical measure of the approximate accuracy of feature importance estimates in deep neural networks. Our results across several large-scale image classification dat…
The (Un)reliability of saliency methods
Pieter-Jan Kindermans, Sara Hooker, Julius Adebayo +5
Saliency methods aim to explain the predictions of deep neural networks. These methods lack reliability when the explanation is sensitive to factors that do not contribute to the m…
Don't Decay the Learning Rate, Increase the Batch Size
Samuel L. Smith, Pieter-Jan Kindermans, Chris Ying +1
It is common practice to decay the learning rate. Here we show one can usually obtain the same learning curve on both training and test sets by instead increasing the batch size du…
SchNet: A continuous-filter convolutional neural network for modeling quantum interactions
Kristof T. Schütt, Pieter-Jan Kindermans, Huziel E. Sauceda +3
Deep learning has the potential to revolutionize quantum chemistry as it is ideally suited to learn representations for structured data and speed up the exploration of chemical spa…
Learning how to explain neural networks: PatternNet and PatternAttribution
Pieter-Jan Kindermans, Kristof T. Schütt, Maximilian Alber +4
DeConvNet, Guided BackProp, LRP, were invented to better understand deep neural networks. We show that these methods do not produce the theoretically correct explanation for a line…
Learning from Label Proportions in Brain-Computer Interfaces: Online Unsupervised Learning with Guarantees
D Hübner, T Verhoeven, K Schmid +3
Objective: Using traditional approaches, a Brain-Computer Interface (BCI) requires the collection of calibration data for new subjects prior to online use. Calibration time can be…
Investigating the influence of noise and distractors on the interpretation of neural networks
Pieter-Jan Kindermans, Kristof Schütt, Klaus-Robert Müller +1
Understanding neural networks is becoming increasingly important. Over the last few years different types of visualisation and explanation methods have been proposed. However, none…