Search Results for author:
Found 30 papers, 18 papers with code
Generative Hierarchical Materials Search
We confirm that GenMS is able to generate common crystal structures such as double perovskites, or spinels, solely from natural language input, and hence can form the foundation for more complex structure generation in near future.
G-Augment: Searching for the Meta-Structure of Data Augmentation Policies for ASR
Data augmentation is a ubiquitous technique used to provide robustness to automatic speech recognition (ASR) training.
Ranked #1 on
Speech Recognition
on CHiME-6 eval
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Do better ImageNet classifiers assess perceptual similarity better?
Perceptual distances between images, as measured in the space of pre-trained deep features, have outperformed prior low-level, pixel-based metrics on assessing perceptual similarity.
No One Representation to Rule Them All: Overlapping Features of Training Methods
Despite being able to capture a range of features of the data, high accuracy models trained with supervision tend to make similar predictions.
Multi-Task Self-Training for Learning General Representations
The results suggest self-training is a promising direction to aggregate labeled and unlabeled training data for learning general feature representations.
Revisiting ResNets: Improved Training and Scaling Strategies
Using improved training and scaling strategies, we design a family of ResNet architectures, ResNet-RS, which are 1. 7x - 2. 7x faster than EfficientNets on TPUs, while achieving similar accuracies on ImageNet.
Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation
Our baseline model outperforms the LVIS 2020 Challenge winning entry by +3. 6 mask AP on rare categories.
Ranked #1 on
Object Detection
on PASCAL VOC 2007
Dataset of Random Relaxations for Crystal Structure Search of Li-Si System
We illustrate the usage of the dataset by training graph neural networks to predict structural relaxations from randomly generated structures.
Kohn-Sham equations as regularizer: building prior knowledge into machine-learned physics
Including prior knowledge is important for effective machine learning models in physics, and is usually achieved by explicitly adding loss terms or constraints on model architectures.
Rethinking Pre-training and Self-training
For example, on the COCO object detection dataset, pre-training benefits when we use one fifth of the labeled data, and hurts accuracy when we use all labeled data.
Ranked #1 on
Semantic Segmentation
on PASCAL VOC 2012 val
Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation
We view this work as a notable step towards building a simple procedure to harness unlabeled video sequences and extra images to surpass state-of-the-art performance on core computer vision tasks.
ReMixMatch: Semi-Supervised Learning with Distribution Matching and Augmentation Anchoring
We improve the recently-proposed ``MixMatch semi-supervised learning algorithm by introducing two new techniques: distribution alignment and augmentation anchoring.
Affinity and Diversity: Quantifying Mechanisms of Data Augmentation
Though data augmentation has become a standard component of deep neural network training, the underlying mechanism behind the effectiveness of these techniques remains poorly understood.
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
Semi-supervised learning (SSL) provides an effective means of leveraging unlabeled data to improve a model's performance.
JAX, M.D.: A Framework for Differentiable Physics
We introduce JAX MD, a software package for performing differentiable physics simulations with a focus on molecular dynamics.
AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
We propose AugMix, a data processing technique that is simple to implement, adds limited computational overhead, and helps models withstand unforeseen corruptions.
Ranked #1 on
Out-of-Distribution Generalization
on ImageNet-W
ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring
Distribution alignment encourages the marginal distribution of predictions on unlabeled data to be close to the marginal distribution of ground-truth labels.
RandAugment: Practical automated data augmentation with a reduced search space
Additionally, due to the separate search phase, these approaches are unable to adjust the regularization strength based on model or dataset size.
Ranked #12 on
Data Augmentation
on ImageNet
JAX MD: End-to-End Differentiable, Hardware Accelerated, Molecular Dynamics in Pure Python
In this work we bring the substantial advances in software that have taken place in machine learning to MD with JAX, M. D.
Learning Data Augmentation Strategies for Object Detection
Importantly, the best policy found on COCO may be transferred unchanged to other detection datasets and models to improve predictive accuracy.
Ranked #6 on
Robust Object Detection
on Cityscapes
A Fourier Perspective on Model Robustness in Computer Vision
Achieving robustness to distributional shift is a longstanding and challenging goal of computer vision.
Using learned optimizers to make models robust to input noise
State-of-the art vision models can achieve superhuman performance on image classification tasks when testing and training data come from the same distribution.
Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation
Deploying machine learning systems in the real world requires both high accuracy on clean data and robustness to naturally occurring corruptions.
AutoAugment: Learning Augmentation Strategies From Data
In our implementation, we have designed a search space where a policy consists of many sub-policies, one of which is randomly chosen for each image in each mini-batch.
Ranked #13 on
Domain Generalization
on VizWiz-Classification
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
On LibriSpeech, we achieve 6. 8% WER on test-other without the use of a language model, and 5. 8% WER with shallow fusion with a language model.
Ranked #1 on
Speech Recognition
on Hub5'00 SwitchBoard
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Accelerated search and design of stretchable graphene kirigami using machine learning
Making kirigami-inspired cuts into a sheet has been shown to be an effective way of designing stretchable materials with metamorphic properties where the 2D shape can transform into complex 3D shapes.
Computational Physics Disordered Systems and Neural Networks
AutoAugment: Learning Augmentation Policies from Data
In our implementation, we have designed a search space where a policy consists of many sub-policies, one of which is randomly chosen for each image in each mini-batch.
Ranked #6 on
Data Augmentation
on ImageNet
Realistic Evaluation of Deep Semi-Supervised Learning Algorithms
However, we argue that these benchmarks fail to address many issues that these algorithms would face in real-world applications.
Machine learning determination of atomic dynamics at grain boundaries
In polycrystalline materials, grain boundaries are sites of enhanced atomic motion, but the complexity of the atomic structures within a grain boundary network makes it difficult to link the structure and atomic dynamics.
Materials Science
Intriguing Properties of Adversarial Examples
Finally, we study the effect of network architectures on adversarial sensitivity.
