Lednet: A Lightweight Encoder-Decoder Network for Real-Time Semantic Segmentation

Wang, Yu; Zhou, Quan; Liu, Jia; Xiong, Jian; Gao, Guangwei; Wu, Xiaofu; Latecki, Longin Jan

doi:10.1109/icip.2019.8803154

Cited by 324 publications

(168 citation statements)

References 24 publications

Supporting

Mentioning

167

Contrasting

Unclassified

Order By: Relevance

“…However, it is not competivie for lower-resolution input images [51]. Lightweight Encoder-Decoder Network (LEDNet) [31] employs an asymmetric encoder-decoder architecture for real-time semantic segmentation. The encoder adopts two new operations (i.e., channel split and shuffle) in each residual block to significantly reduce the computational cost, while the decoder uses an attention pyramid network to further reduce the network complexity.…”

Section: B Real-time Semantic Segmentation Methodsmentioning

confidence: 99%

“…To illustrate this dilemma, Fig. 1 gives the accuracy (mIoU) and inference speed (frames per second (fps)) obtained by several state-of-the-art methods, including FCN-8s [9], CRF-RNN [17], DeepLab [10], DeepLabv2 [12], DeepLabv3+ [13], ResNet-38 [18], PSPNet [11], DUC [19], RefineNet [20], LRR [21], DPN [22], FRRN [23], TwoColumn [24], SegNet [25], SQNet [26], ENet [27], arXiv:2003.08736v2 [cs.CV] 3 Apr 2020 ERFNet [28], ICNet [29], SwiftNetRN [30], LEDNet [31], BiSeNet1 [32], BiSeNet2 [32], DFANet [33] and our proposed method, on the Cityscapes test dataset. Clearly, how to achieve a good tradeoff between accuracy and speed is still a challenging problem.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Real-Time High-Performance Semantic Image Segmentation of Urban Street Scenes

Dong

Yan

Shen

et al. 2021

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

Deep Convolutional Neural Networks (DCNNs) have recently shown outstanding performance in semantic image segmentation. However, state-of-the-art DCNN-based semantic segmentation methods usually suffer from high computational complexity due to the use of complex network architectures. This greatly limits their applications in the real-world scenarios that require real-time processing. In this paper, we propose a real-time high-performance DCNN-based method for robust semantic segmentation of urban street scenes, which achieves a good trade-off between accuracy and speed. Specifically, a Lightweight Baseline Network with Atrous convolution and Attention (LBN-AA) is firstly used as our baseline network to efficiently obtain dense feature maps. Then, the Distinctive Atrous Spatial Pyramid Pooling (DASPP), which exploits the different sizes of pooling operations to encode the rich and distinctive semantic information, is developed to detect objects at multiple scales. Meanwhile, a Spatial detail-Preserving Network (SPN) with shallow convolutional layers is designed to generate highresolution feature maps preserving the detailed spatial information. Finally, a simple but practical Feature Fusion Network (FFN) is used to effectively combine both shallow and deep features from the semantic branch (DASPP) and the spatial branch (SPN), respectively. Extensive experimental results show that the proposed method respectively achieves the accuracy of 73.6% and 68.0% mean Intersection over Union (mIoU) with the inference speed of 51.0 fps and 39.3 fps on the challenging Cityscapes and CamVid test datasets (by only using a single NVIDIA TITAN X card). This demonstrates that the proposed method offers excellent performance at the real-time speed for semantic segmentation of urban street scenes.

show abstract

Section: B Real-time Semantic Segmentation Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Real-Time High-Performance Semantic Image Segmentation of Urban Street Scenes

Dong

Yan

Shen

et al. 2021

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

show abstract

“…We compare our method with six state-of-the-art (SOTA) algorithms, including U-Net [6], Attention-Unet [20], GCN [21], CE-Net [52], HRNet [63], LEDNet [64]. Their original implementations were kept and the same experimental conditions were used.…”

Section: E Comparison With Other Deep Learning Methodsmentioning

confidence: 99%

HIFUNet: Multi-Class Segmentation of Uterine Regions From MR Images Using Global Convolutional Networks for HIFU Surgery Planning

Zhang

Yang

et al. 2020

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

Accurate segmentation of uterus, uterine fibroids, and spine from MR images is crucial for high intensity focused ultrasound (HIFU) therapy but remains still difficult to achieve because of 1) the large shape and size variations among individuals, 2) the low contrast between adjacent organs and tissues, and 3) the unknown number of uterine fibroids. To tackle this problem, in this paper, we propose a large kernel Encoder-Decoder Network based on a 2D segmentation model. The use of this large kernel can capture multi-scale contexts by enlarging the valid receptive field. In addition, a deep multiple atrous convolution block is also employed to enlarge the receptive field and extract denser feature maps. Our approach is compared to both conventional and other deep learning methods and the experimental results conducted on a large dataset show its effectiveness.

show abstract

“…2017) which are standard segmentation networks with increasing complexity and also to the following lighter architectures: LEDNet (Wang et al, 2019a), ERFNet (Romera et al, 2017) and D3Net (Carvalho et al, 2018). Figure 7 shows the results obtained with the different architectures under the same training and evaluating conditions.…”

Section: Influence Of the Network Backbonementioning

confidence: 99%

Disir: Deep Image Segmentation With Interactive Refinement

Lenczner

Saux²,

Luminari³

et al. 2020

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. This paper presents an interactive approach for multi-class segmentation of aerial images. Precisely, it is based on a deep neural network which exploits both RGB images and annotations. Starting from an initial output based on the image only, our network then interactively refines this segmentation map using a concatenation of the image and user annotations. Importantly, user annotations modify the inputs of the network – not its weights – enabling a fast and smooth process. Through experiments on two public aerial datasets, we show that user annotations are extremely rewarding: each click corrects roughly 5000 pixels. We analyze the impact of different aspects of our framework such as the representation of the annotations, the volume of training data or the network architecture. Code is available at this address.

show abstract

Lednet: A Lightweight Encoder-Decoder Network for Real-Time Semantic Segmentation

Cited by 324 publications

References 24 publications

Real-Time High-Performance Semantic Image Segmentation of Urban Street Scenes

Real-Time High-Performance Semantic Image Segmentation of Urban Street Scenes

HIFUNet: Multi-Class Segmentation of Uterine Regions From MR Images Using Global Convolutional Networks for HIFU Surgery Planning

Disir: Deep Image Segmentation With Interactive Refinement

Contact Info

Product

Resources

About