Gated Feedback Refinement Network for Dense Image Labeling
Citations
7,113 citations
Cites methods from "Gated Feedback Refinement Network f..."
...Encoder-decoder: The encoder-decoder networks have been successfully applied to many computer vision tasks, including human pose estimation [53], object detection [45, 66, 19], and semantic segmentation [49, 54, 61, 3, 43, 59, 57, 33, 76, 20]....
[...]
5,691 citations
Cites background or methods from "Gated Feedback Refinement Network f..."
...Second, the encoder-decoder structure [3, 61, 20, 45, 60, 58, 33] exploits multi-scale features from the encoder part and recovers the spatial resolution from the decoder part....
[...]
...More recently, RefineNet [45] and [60, 58, 33] have demonstrated the effectiveness of models based on encoder-decoder structure on several semantic segmentation benchmarks....
[...]
3,423 citations
1,278 citations
Cites background from "Gated Feedback Refinement Network f..."
...Other works include: light upsample process [7], [24], [92], [152], possibly with dilated convolutions used in the backbone [63], [89], [113]; light downsample and heavy upsample processes [141], recombinator networks [55]; improving skip connections with more or complicated convolutional units [64], [111], [180], as well as sending information from low-resolution skip connections to highresolution skip connections [189] or exchanging information between them [49]; studying the details of the upsample process [147]; combining multi-scale pyramid representations [22], [154]; stacking multiple DeconvNets/UNets/Hourglass [44], [149] with dense connections [135]....
[...]
1,162 citations
References
49,914 citations
28,225 citations
"Gated Feedback Refinement Network f..." refers background or methods in this paper
...LRN [14] achieves 64.2% mean IoU which outperforms FCN [21] and SegNet [1]....
[...]
...Following prior work [3, 21, 1], we augment the training set with extra labeled PASCAL VOC images from [11]....
[...]
...Other approaches which use refinement process straight away combines convolution features (using skip connections [21]) with coarse label maps through concatenation to generate a new label map....
[...]
...0% mean IoU accuracy compared to encoderdecoder based architecture ([22, 31, 21])....
[...]
...Following [22, 3, 21], we add two convolution layers conv6 and conv7 at the end of encoder....
[...]
15,935 citations
"Gated Feedback Refinement Network f..." refers background or methods in this paper
...PASCAL VOC 2012 [8] is a challenging dataset for semantic segmentation....
[...]
...This dataset contains images of horse and cow images only, which are manually selected from the PASCAL VOC 2010 benchmark [8] based on most observable instances....
[...]
15,313 citations
13,468 citations
"Gated Feedback Refinement Network f..." refers background or methods in this paper
...LRN [14] achieves 64.2% mean IoU which outperforms FCN [21] and SegNet [1]....
[...]
...Our G-FRNet is inspired by the encoder-decoder architecture [22, 1, 14] for dense image labeling....
[...]
...Following prior work [3, 21, 1], we augment the training set with extra labeled PASCAL VOC images from [11]....
[...]
...However, there are only few recent methods [22, 1] that use a simpler encoder-decoder architecture for this problem, and it is most natural to compare our approach directly with this related family of models....
[...]
...LRN [14] outperforms SegNet [1] by more than 11% (in terms of mean IoU) while our approach (i....
[...]