DAG-Recurrent Neural Networks For Scene Labeling

CVPR 2016 Bing ShuaiZhen ZuoGang WangBing Wang

In image labeling, local representations for image units are usually generated from their surrounding image patches, thus long-range contextual information is not effectively encoded. In this paper, we introduce recurrent neural networks (RNNs) to address this issue... (read more)

PDF Abstract CVPR 2016 PDF CVPR 2016 Abstract

Code


No code implementations yet. Submit your code now
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Semantic Segmentation COCO-Stuff test DAG-RNN (VGG-16) mIoU 31.2% # 9

Methods used in the Paper