Learning a Discriminative Feature Network for Semantic Segmentation

By Changqian Yu, Jingbo Wang, Chao Peng, Changxin Gao, Gang Yu, Nong Sang. 2018

818 citations recorded by the source corpus.

Most existing methods of semantic segmentation still suffer from two aspects of challenges: intra-class inconsistency and inter-class indistinction. To tackle these two problems, we propose a Discriminative Feature Network (DFN), which contains two sub-networks: Smooth Network and Border Network. Specifically, to handle the intra-class inconsistency problem, we specially design a Smooth Network with Channel Attention Block and global average pooling to select the more discriminative features. Furthermore, we propose a Border Network to make the bilateral features of boundary distinguishable with deep semantic boundary supervision. Based on our proposed DFN, we achieve state-of-the-art performance 86.2% mean IOU on PASCAL VOC 2012 and 80.3% mean IOU on Cityscapes dataset.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

CCNet: Criss-Cross Attention for Semantic Segmentation (2018, methodology): “Most of methods [5, 22, 40, 27, 30, 41, 35, 19, 42, 36] adopt the same backbone as ours and the others [32, 34] utilize stronger backbones.”
Deep High-Resolution Representation Learning for Visual Recognition (2019, neutral): “DFN [167] ResNet-101 79.”
Attention-Guided Unified Network for Panoptic Segmentation (2018, background): “In the scope of scene understanding, [42] and [43] aggregated global contextual information as well as class-dependent features by channel-attention operations.”
Strip Pooling: Rethinking Spatial Pooling for Scene Parsing (2020, neutral): “2% DFN [56] CVPR’18 ResNet-101 79.”
SPGNet: Semantic Prediction Guidance for Scene Parsing (2019, neutral): “5B DFN [71] ResNet-101 79.”
OCNet: Object Context Network for Scene Parsing (2018, neutral): “t-101 73.6 SAC [25]z ICCV2017 ResNet-101 78.1 DUC-HDC [16]z WACV2018 ResNet-101 77.6 AAF [6]z ECCV2018 ResNet-101 79.1 BiSeNet [21]z ECCV2018 ResNet-101 78.9 PSANet [27]z ECCV2018 ResNet-101 80.1 DFN [22]z CVPR2018 ResNet-101 79.3 DSSPN [8]z CVPR2018 ResNet-101 77.8 DepthSeg [7]z CVPR2018 ResNet-101”
BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation (2018, methodology): “Like the DFN [36], they learn the global context as attention and revise the features.”
Image Segmentation Using Deep Learning: A Survey (2020, background): “Fortunately, with the increasing popularity of deep learning models, the trend has been TABLE 1 Accuracies of Segmentation Models on the PASCALVOC Test Set Method Backbone mIoU FCN [30] VGG-16 62.2 CRF-RNN [38] - 72.0 CRF-RNN [38] - 74.7 BoxSup* [119] - 75.1 Piecewise [39] - 78.0 DPN [40] - 77.5 Dee”
Learning Dynamic Routing for Semantic Segmentation (2020, methodology): “Based on the welldesigned FCN [24] and U-shape architecture [28], numerous works have been proposed to model global context by capturing larger receptive field [43, 4, 5, 6, 41] or establishing pixel-wise relationships [44, 18, 12, 31].”
An End-To-End Network for Panoptic Segmentation (2019, methodology): “The encoder-decoder structure such as UNet [1, 38, 42, 43, 47] can gradually recover resolution and capture more object details.”
Improving Semantic Segmentation via Decoupled Body and Edge Supervision (2020, neutral): “1 DFN [57] ResNet-101 79.”
CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation With Transformers (2022, methodology): “Additional FCNbased methods improve dense semantic segmentation by refining context priors [43], [44], [45], [46], [47], [48], [49], enhancing boundary cues [50], [51], [52], and appending various attention modules [53], [54], [55], [56], [57] to boost the performance.”
Prototype-based Incremental Few-Shot Segmentation (2020, background): “State-of-the-art models use a fully convolutional encoder-decoder networks [1, 26], integrate contextual information on pixel-level features in different ways, e.g. through pyramids [5, 6, 7, 23, 59, 60], or attention [13, 51, 52, 54, 55, 57].”
Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation (2020, neutral): “For instance, DFN [41] introduces a channel attention block to select the more discriminative features from multi-level feature maps to get more accurate semantic information.”
BiSeNet V2: Bilateral Network with Guided Aggregation for Real-Time Semantic Segmentation (2020, methodology): “…al., 2016), ESPNet (Mehta et al., 2018), ESPNetV2 (Mehta et al., 2019), ERFNet (Romera et al., 2018), Fast-SCNN (Poudel et al., 2019), ICNet (Zhao et al., 2018a), DABNet (Li et al., 2019a), DFANet (Li et al., 2019b), GUN (Mazzini, 2018), SwiftNet (Or-sic et al., 2019), BiSeNetV1 (Yu et al., 2018a).”