BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition | 2 | 0.37 | 2022 |
DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection. | 0 | 0.34 | 2022 |
STraTA - Self-Training with Task Augmentation for Better Few-shot Learning. | 0 | 0.34 | 2021 |
CoAtNet: Marrying Convolution and Attention for All Data Sizes. | 0 | 0.34 | 2021 |
Searching for Fast Model Families on Datacenter Accelerators | 0 | 0.34 | 2021 |
Meta Pseudo Labels | 0 | 0.34 | 2021 |
Evolving Reinforcement Learning Algorithms. | 0 | 0.34 | 2021 |
EfficientNetV2: Smaller Models and Faster Training | 0 | 0.34 | 2021 |
Pay Attention to MLPs. | 0 | 0.34 | 2021 |
Towards Domain-Agnostic Contrastive Learning | 0 | 0.34 | 2021 |
Adversarial Examples Improve Image Recognition | 5 | 0.48 | 2020 |
AutoML-Zero: Evolving Machine Learning Algorithms From Scratch | 0 | 0.34 | 2020 |
PyGlove: Symbolic Programming for Automated Machine Learning | 0 | 0.34 | 2020 |
SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization | 5 | 0.42 | 2020 |
Can Weight Sharing Outperform Random Architecture Search? An Investigation With TuNAS | 4 | 0.40 | 2020 |
Go Wide, Then Narrow: Efficient Training of Deep Thin Networks | 0 | 0.34 | 2020 |
Randaugment: Practical automated data augmentation with a reduced search space | 14 | 0.68 | 2020 |
Pre-Training Transformers as Energy-Based Cloze Models. | 0 | 0.34 | 2020 |
Unsupervised data augmentation for consistency training | 1 | 0.35 | 2020 |
Rethinking Pre-training and Self-training | 0 | 0.34 | 2020 |
MnasFPN: Learning Latency-aware Pyramid Architecture for Object Detection on Mobile Devices | 0 | 0.34 | 2020 |
Evolving Normalization-Activation Layers | 0 | 0.34 | 2020 |
Self-Training With Noisy Student Improves ImageNet Classification | 22 | 0.74 | 2020 |
Learning Data Augmentation Strategies for Object Detection. | 6 | 0.53 | 2020 |
Neural Input Search for Large Scale Recommendation Models | 8 | 0.47 | 2020 |
EfficientDet: Scalable and Efficient Object Detection | 5 | 0.42 | 2020 |
XLNet: Generalized Autoregressive Pretraining for Language Understanding. | 28 | 0.72 | 2019 |
Mixtape: Breaking the Softmax Bottleneck Efficiently | 0 | 0.34 | 2019 |
High Fidelity Video Prediction with Large Stochastic Recurrent Neural Networks | 0 | 0.34 | 2019 |
MixConv - Mixed Depthwise Convolutional Kernels. | 2 | 0.37 | 2019 |
Saccader: Improving Accuracy of Hard Attention Models for Vision | 0 | 0.34 | 2019 |
The Evolved Transformer. | 0 | 0.34 | 2019 |
Searching For Mobilenetv3 | 42 | 1.21 | 2019 |
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. | 72 | 1.30 | 2019 |
Unsupervised Data Augmentation. | 0 | 0.34 | 2019 |
GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism | 7 | 0.42 | 2019 |
BAM! Born-Again Multi-Task Networks for Natural Language Understanding | 2 | 0.36 | 2019 |
Selfie: Self-supervised Pretraining for Image Embedding. | 0 | 0.34 | 2019 |
The Evolved Transformer. | 0 | 0.34 | 2019 |
The Effect of Network Width on Stochastic Gradient Descent and Generalization: an Empirical Study. | 0 | 0.34 | 2019 |
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition. | 9 | 0.49 | 2019 |
Natural Questions: a Benchmark for Question Answering Research. | 0 | 0.34 | 2019 |
CondConv: Conditionally Parameterized Convolutions for Efficient Inference | 1 | 0.35 | 2019 |
Neural Program Synthesis with Priority Queue Training. | 7 | 0.43 | 2018 |
Can Deep Reinforcement Learning Solve Erdos-Selfridge-Spencer Games? | 4 | 0.48 | 2018 |
Learning Longer-term Dependencies in RNNs with Auxiliary Losses. | 12 | 0.51 | 2018 |
Faster Discovery of Neural Architectures by Searching for Paths in a Large Model | 6 | 0.50 | 2018 |
AirDialogue: An Environment for Goal-Oriented Dialogue Research. | 3 | 0.37 | 2018 |
QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension. | 53 | 1.12 | 2018 |
A Hierarchical Model for Device Placement | 8 | 0.45 | 2018 |