Semantic Flow for Fast and Accurate Scene Parsing

Li, Xiangtai; You, Ansheng; Zhu, Zhen; Zhao, Houlong; Yang, Maoke; Yang, Kuiyuan; Tan, Shuping; Tong, Yunhai

doi:10.1007/978-3-030-58452-8_45

Cited by 251 publications

(140 citation statements)

References 58 publications

Supporting

Mentioning

139

Contrasting

Order By: Relevance

“…Therefore, the kernel size in AEL is finally set as 5. Furthermore, CFM is also compared with other general feature fusion modules, including lateral connections in [39], spatial pyramid pooling with dilated convolutions in [40], skip connections in [38], non-local fusion in [42] and semantic flows in [61]. In this group of experiments, the baseline is unified as FCN.…”

Section: Methodsmentioning

confidence: 99%

Controllable Fused Semantic Segmentation with Adaptive Edge Loss for Remote Sensing Parsing

Sun¹,

Xia

Dai³

2022

Remote Sensing

View full text Add to dashboard Cite

High-resolution remote sensing images have been put into the application in remote sensing parsing. General remote sensing parsing methods based on semantic segmentation still have limitations, which include frequent neglect of tiny objects, high complexity in image understanding and sample imbalance. Therefore, a controllable fusion module (CFM) is proposed to alleviate the problem of implicit understanding of complicated categories. Moreover, an adaptive edge loss function (AEL) was proposed to alleviate the problem of the recognition of tiny objects and sample imbalance. Our proposed method combining CFM and AEL optimizes edge features and body features in a coupled mode. The verification on Potsdam and Vaihingen datasets shows that our method can significantly improve the parsing effect of satellite images in terms of mIoU and MPA.

show abstract

Section: Methodsmentioning

confidence: 99%

Controllable Fused Semantic Segmentation with Adaptive Edge Loss for Remote Sensing Parsing

Sun¹,

Xia

Dai³

2022

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Li et al proposed DFANet 20 in which the multiple network branches are used to process multiscale input images to achieve more accurate segmentation results. SFNet 16 guides feature map up-sampling by learning semantic flow information from low-resolution feature maps to high-resolution feature maps, and stacks feature maps at multiple scales to generate the final result. CARNet 21 proposes the CAR module to guide the fusion of adjacent scale features by the attention mechanism.…”

Section: Multiscale Methodsmentioning

confidence: 99%

“…Zhao et al proposed ICNet 15 in which the semantic information of low-resolution graphs was effectively utilized by cascading multiple scales of inputs and detailed information of high-resolution graphs. In recent work, Li et al proposed SFNet 16 in which the semantic flow up-sampling is used to guide feature graph up-sampling by learning semantic flow information from low-resolution feature graphs to high-resolution feature graphs. On the other hand, Zha et al proposed EACNet, 17 which uses an improved nonlocal module to establish spatial correlation for the segmentation graphs output from the real-time semantic segmentation backbone network.…”

Section: Real-time Semantic Segmentationmentioning

confidence: 99%

ASFNet: Adaptive multiscale segmentation fusion network for real‐time semantic segmentation

Zha

Liu

Yang

et al. 2021

Computer Animation & Virtual

View full text Add to dashboard Cite

Recently, the development of deep learning has facilitated continuous progress in the field of computer vision. Pixel-level semantic segmentation serves as a fundamental task in computer vision. It achieves significant results by connecting wider and deeper backbone networks and building fine-grained segmentation heads. However, applications such as self-driving cars are more critical to the computational speed of the algorithms. The trade-off between accuracy and real-time performance of existing algorithms is still a challenging task. To address this challenge, this article proposes an adaptive multiscale segmentation fusion network to fuse multiscale contextual, which designs an adaptive multiscale segmentation fusion module based on an attention mechanism. Using segmentation fusion instead of feature fusion, the multiscale segmentation results are aggregated to obtain more precise segmentation results. The final results achieved 70.9% mIoU of accuracy in the Cityspace test set, processing images at 61 FPS when the input is 1024 × 2048. In addition, when adjusting the input size to 512 × 1024, the images are processed at 185 FPS.

show abstract

“…SNE-RoadSeg [50] introduces a surface normal estimator to infer surface normal information from dense depth images for freespace segmentation. SFNet [51] integrates a Flow Alignment Module into the feature pyramid structure for learning the Semantic Flow between adjacent level feature maps and efficiently broadcasting high-level features into high-resolution features.…”

Section: Semantic Segmentationmentioning

confidence: 99%

DPANet: Dual Pooling‐aggregated Attention Network for fish segmentation

Zhang

Bao

2021

IET Computer Vision

View full text Add to dashboard Cite

The sustainable development of marine fisheries depends on the accurate measurement of data on fish stocks. Semantic segmentation methods based on deep learning can be applied to automatically obtain segmentation masks of fish in images to obtain measurement data. However, general semantic segmentation methods cannot accurately segment fish objects in underwater images. In this study, a Dual Pooling-aggregated Attention Network (DPANet) to adaptively capture long-range dependencies through an efficient and computing-friendly manner to enhance feature representation and improve segmentation performance is proposed. Specifically, a novel pooling-aggregate position attention module and a poolingaggregate channel attention module are designed to aggregate contexts in the spatial dimension and channel dimension, respectively. These two modules adopt pooling operations along the channel dimension and along the spatial dimension to aggregate information, respectively, thus reducing computational costs. In these modules, attention maps are generated by four different paths and are aggregated into one. The authors conduct extensive experiments to validate the effectiveness of the DPANet and achieve new state-ofthe-art segmentation performance on the well-known fish image dataset DeepFish as well as on the underwater image dataset SUIM, achieving a Mean IoU score of 91.08% and 85.39% respectively, while significantly reducing FLOPs of attention modules by about 93%.

show abstract

Semantic Flow for Fast and Accurate Scene Parsing

Cited by 251 publications

References 58 publications

Controllable Fused Semantic Segmentation with Adaptive Edge Loss for Remote Sensing Parsing

Controllable Fused Semantic Segmentation with Adaptive Edge Loss for Remote Sensing Parsing

ASFNet: Adaptive multiscale segmentation fusion network for real‐time semantic segmentation

DPANet: Dual Pooling‐aggregated Attention Network for fish segmentation

Contact Info

Product

Resources

About