MobileNetV2: Inverted Residuals and Linear Bottlenecks

CVPR 2018 • tensorflow/models •

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.

IMAGE CLASSIFICATION OBJECT DETECTION PERSON RE-IDENTIFICATION RETINAL OCT DISEASE CLASSIFICATION SEMANTIC SEGMENTATION

MnasFPN: Learning Latency-aware Pyramid Architecture for Object Detection on Mobile Devices

CVPR 2020 • tensorflow/models •

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.

OBJECT DETECTION

Searching for Efficient Multi-Scale Architectures for Dense Image Prediction

NeurIPS 2018 • tensorflow/models •

Recent progress has demonstrated that such meta-learning methods may exceed scalable human-invented architectures on image classification tasks.

IMAGE CLASSIFICATION META-LEARNING SEMANTIC SEGMENTATION STREET SCENE PARSING

Adversarial Training Methods for Semi-Supervised Text Classification

25 May 2016 • tensorflow/models •

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.

SEMI SUPERVISED TEXT CLASSIFICATION SEMI-SUPERVISED TEXT CLASSIFICATION SENTIMENT ANALYSIS WORD EMBEDDINGS

Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation

CVPR 2019 • tensorflow/models •

Therefore, we propose to search the network level structure in addition to the cell level structure, which forms a hierarchical architecture search space.

IMAGE CLASSIFICATION NEURAL ARCHITECTURE SEARCH SEMANTIC SEGMENTATION

Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation

ECCV 2020 • tensorflow/models •

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.

OPTICAL FLOW ESTIMATION PANOPTIC SEGMENTATION PATCH MATCHING SCENE SEGMENTATION

Trust-PCL: An Off-Policy Trust Region Method for Continuous Control

ICLR 2018 • tensorflow/models •

When evaluated on a number of continuous control tasks, Trust-PCL improves the solution quality and sample efficiency of TRPO.

CONTINUOUS CONTROL

Bridging the Gap Between Value and Policy Based Reinforcement Learning

NeurIPS 2017 • tensorflow/models •

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.

Q-LEARNING

REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models

NeurIPS 2017 • tensorflow/models •

Learning in models with discrete latent variables is challenging due to high variance gradient estimators.

LATENT VARIABLE MODELS

Categorical Reparameterization with Gumbel-Softmax

3 Nov 2016 • tensorflow/models •

Categorical variables are a natural choice for representing discrete structure in the world.