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.
Ranked #28 on Semantic Segmentation on PASCAL Context
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.
Ranked #128 on Image Classification on ImageNet
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.
Ranked #10 on Semantic Segmentation on PASCAL VOC 2012 val
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)
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 #5 on Panoptic Segmentation on COCO panoptic
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).
Ranked #75 on Image Classification on ImageNet
TensorFlow is an interface for expressing machine learning algorithms, and an implementation for executing such algorithms.
We propose a new benchmark corpus to be used for measuring progress in statistical language modeling.
Ranked #15 on Language Modelling on One Billion Word