ParseNet: Looking Wider to See Better

15 Jun 2015tensorflow/models

When we add our proposed global feature, and a technique for learning normalization parameters, accuracy increases consistently even over our improved versions of the baselines.

SEMANTIC SEGMENTATION

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

11 Feb 2015tensorflow/models

Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change.

IMAGE CLASSIFICATION

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

2 Jun 2016tensorflow/models

ASPP probes an incoming convolutional feature layer with filters at multiple sampling rates and effective fields-of-views, thus capturing objects as well as image context at multiple scales.

SEMANTIC SEGMENTATION

Rethinking Atrous Convolution for Semantic Image Segmentation

17 Jun 2017tensorflow/models

To handle the problem of segmenting objects at multiple scales, we design modules which employ atrous convolution in cascade or in parallel to capture multi-scale context by adopting multiple atrous rates.

Ranked #4 on Semantic Segmentation on PASCAL VOC 2012 val (using extra training data)

SEMANTIC SEGMENTATION

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 SEMANTIC SEGMENTATION

Xception: Deep Learning with Depthwise Separable Convolutions

CVPR 2017 tensorflow/models

We present an interpretation of Inception modules in convolutional neural networks as being an intermediate step in-between regular convolution and the depthwise separable convolution operation (a depthwise convolution followed by a pointwise convolution).

IMAGE CLASSIFICATION

TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems

14 Mar 2016tensorflow/models

TensorFlow is an interface for expressing machine learning algorithms, and an implementation for executing such algorithms.

DIMENSIONALITY REDUCTION

One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling

11 Dec 2013tensorflow/models

We propose a new benchmark corpus to be used for measuring progress in statistical language modeling.

LANGUAGE MODELLING