In this paper we describe a new mobile architecture, MobileNetV2, that improves the state of the art performance of mobile models on multiple tasks and benchmarks as well as across a spectrum of different model sizes.
Ranked #4 on Retinal OCT Disease Classification on OCT2017
We propose MnasFPN, a mobile-friendly search space for the detection head, and combine it with latency-aware architecture search to produce efficient object detection models.
Ranked #98 on Object Detection on COCO test-dev
Recent progress has demonstrated that such meta-learning methods may exceed scalable human-invented architectures on image classification tasks.
Ranked #3 on Human Part Segmentation on PASCAL-Person-Part
Adversarial training provides a means of regularizing supervised learning algorithms while virtual adversarial training is able to extend supervised learning algorithms to the semi-supervised setting.
Ranked #9 on Sentiment Analysis on IMDb
Therefore, we propose to search the network level structure in addition to the cell level structure, which forms a hierarchical architecture search space.
Ranked #5 on Semantic Segmentation on Cityscapes val
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.
When evaluated on a number of continuous control tasks, Trust-PCL improves the solution quality and sample efficiency of TRPO.
We establish a new connection between value and policy based reinforcement learning (RL) based on a relationship between softmax temporal value consistency and policy optimality under entropy regularization.
Learning in models with discrete latent variables is challenging due to high variance gradient estimators.