Efficientnet: Rethinking model scaling for convolutional neural networks
Abstract Convolutional Neural Networks (ConvNets) are commonly developed at a fixed
resource budget, and then scaled up for better accuracy if more resources are given. In this�…
resource budget, and then scaled up for better accuracy if more resources are given. In this�…
Randaugment: Practical automated data augmentation with a reduced search space
Recent work on automated augmentation strategies has led to state-of-the-art results in
image classification and object detection. An obstacle to a large-scale adoption of these�…
image classification and object detection. An obstacle to a large-scale adoption of these�…
Mnasnet: Platform-aware neural architecture search for mobile
Designing convolutional neural networks (CNN) for mobile devices is challenging because
mobile models need to be small and fast, yet still accurate. Although significant efforts have�…
mobile models need to be small and fast, yet still accurate. Although significant efforts have�…
The flan collection: Designing data and methods for effective instruction tuning
We study the design decision of publicly available instruction tuning methods, by
reproducing and breaking down the development of Flan 2022 (Chung et al., 2022)�…
reproducing and breaking down the development of Flan 2022 (Chung et al., 2022)�…
Scaling up visual and vision-language representation learning with noisy text supervision
Pre-trained representations are becoming crucial for many NLP and perception tasks. While
representation learning in NLP has transitioned to training on raw text without human�…
representation learning in NLP has transitioned to training on raw text without human�…
Efficientnetv2: Smaller models and faster training
This paper introduces EfficientNetV2, a new family of convolutional networks that have faster
training speed and better parameter efficiency than previous models. To develop these�…
training speed and better parameter efficiency than previous models. To develop these�…
Regularized evolution for image classifier architecture search
The effort devoted to hand-crafting neural network image classifiers has motivated the use of
architecture search to discover them automatically. Although evolutionary algorithms have�…
architecture search to discover them automatically. Although evolutionary algorithms have�…
Building high-level features using large scale unsupervised learning
QV Le�- 2013 IEEE international conference on acoustics�…, 2013 - ieeexplore.ieee.org
We consider the problem of building high-level, class-specific feature detectors from only
unlabeled data. For example, is it possible to learn a face detector using only unlabeled�…
unlabeled data. For example, is it possible to learn a face detector using only unlabeled�…
Large scale distributed deep networks
Recent work in unsupervised feature learning and deep learning has shown that being able
to train large models can dramatically improve performance. In this paper, we consider the�…
to train large models can dramatically improve performance. In this paper, we consider the�…
Lamda: Language models for dialog applications
We present LaMDA: Language Models for Dialog Applications. LaMDA is a family of
Transformer-based neural language models specialized for dialog, which have up to 137B�…
Transformer-based neural language models specialized for dialog, which have up to 137B�…