Gated Feedback Refinement Network for Dense Image Labeling

By Md. Amirul Islam, Mrigank Rochan, Neil D. B. Bruce, Yang Wang. 2017

210 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Global Pooling, More than Meets the Eye: Position Information is Encoded Channel-Wise in CNNs (2021, neutral): “We now aim to demonstrate that complex networks trained for position-based tasks, such as semantic segmentation [3, 17], have a signiﬁcant reliance on the position information encoded channel-wise in their latent representations.”
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation (2018, methodology): “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].”
EfficientDet: Scalable and Efficient Object Detection (2019, background): “…[19] adds an extra bottom-up path aggregation network on top of FPN; STDL [35] proposes a scale-transfer module to exploit cross-scale features; M2det [34] proposes a U-shape module to fuse multi-scale features, and G-FRNet [1] introduces gate units for controlling information ﬂow across features.”
NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection (2019, methodology): “In addition to manually design the cross-scale connections, [5, 27] propose to learn the connections through gating mechanism for visual counting and dense label predictions.”
Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation (2019, methodology): “In addition to adopting those networks as backbones for semantic segmentation, one could employ the encoder-decoder structures [64, 2, 55, 44, 60, 58, 33, 79, 18, 11, 87, 83] which ef-ﬁciently captures the long-range context information while keeping the detailed object boundaries.”
Deep High-Resolution Representation Learning for Visual Recognition (2019, background): “…downsample and heavy up-sample 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 high-resolution skip connections [189] or exchanging…”
ExFuse: Enhancing Feature Fusion for Semantic Segmentation (2018, positive): “We use two public-available semantic segmentation benchmarks – PASCAL VOC 2012 [20] and Semantic Boundaries Dataset [29] – for training and evaluate performances on PASCAL VOC 2012 validation set, which is consistent with many previous work [1,2,3,4,5,6,8,9,10,13,11,12,27].”
SPGNet: Semantic Prediction Guidance for Scene Parsing (2019, methodology): “The systems [1,3,11,36,43,45,46,48,62,65,74], employing the single-stage encoder-decoder structure ( i.e ., the encoder-decoder structure is stacked only once), have demonstrated outstanding performance on several semantic segmentation benchmarks.”
DeeperLab: Single-Shot Image Parser (2019, background): “Typically, the encoder-decoder networks [48, 45, 46, 49, 50, 51, 52, 53, 54, 7, 55, 56] capture the context information in the encoder path and recover the object boundary in the decoder path.”
Affinity Derivation and Graph Merge for Instance Segmentation (2018, background): “Most recently, Chen et al. proposes Deeplabv3+ [8] by introducing encoder-decoder structure [41,36,16,27] to [7] and achieves promising performance.”
DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution (2020, unknown): “G-FRNet [1] adds feedback with gating units.”
Survey on semantic segmentation using deep learning techniques (2019, background): “Islam et al. [90] proposed Gated Feedback Reﬁnement Network (G-FRNet), an encoder-decoder style architecture.”
Learning Spatial Fusion for Single-Shot Object Detection (2019, background): “[1] adopts element-wise product in two adjacent feature maps to form a gate unit in a top-down manner for dense label prediction.”
Attentive Feedback Network for Boundary-Aware Salient Object Detection (2019, methodology): “[11] applies gate units between each encoder and decoder blocks as attention models.”
How Much Position Information Do Convolutional Neural Networks Encode? (2020, background): “…and detection (Redmon et al., 2016; Ren et al., 2015), face recognition (Taigman et al., 2014), semantic segmentation (Long et al., 2015; Chen et al., 2018; Noh et al., 2015; Islam et al., 2017) and saliency detection (Cornia et al., 2018; Li et al., 2014; Jia & Bruce, 2019; Islam et al., 2018).”
CFCM: Segmentation via Coarse to Fine Context Memory (2018, background): “An exception is represented by the gated feedback reﬁnement network by Islam et al. [11] which comprise gate units to control the information ﬂow and ﬁlter out ambiguity.”
On the Iterative Refinement of Densely Connected Representation Levels for Semantic Segmentation (2018, methodology): “Efforts in this direction include iterative concatenation of feature maps [17, 21]; fusing upsampled feature maps with different receptive fields prior to the softmax classifier [5], along the network [27, 1] or by means of two interacting processing streams operating at different resolutions [33]; ”