mlsanityData to 7 Oct 2026

STDC-MA Network for Semantic Segmentation

arXiv 2205.04639 ↗First posted 10 May 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Semantic segmentation is applied extensively in autonomous driving and intelligent transportation with methods that highly demand spatial and semantic information. Here, an STDC-MA network is proposed to meet these demands. First, the STDC-Seg structure is employed in STDC-MA to ensure a lightweight and efficient structure. Subsequently, the feature alignment module (FAM) is applied to understand the offset between high-level and low-level features, solving the problem of pixel offset related to upsampling on the high-level feature map. Our approach implements the effective fusion between high-level features and low-level features. A hierarchical multiscale attention mechanism is adopted to reveal the relationship among attention regions from two different input sizes of one image. Through this relationship, regions receiving much attention are integrated into the segmentation results, thereby reducing the unfocused regions of the input image and improving the effective utilization of multiscale features. STDC- MA maintains the segmentation speed as an STDC-Seg network while improving the segmentation accuracy of small objects. STDC-MA was verified on the verification set of Cityscapes. The segmentation result of STDC-MA attained 76.81% mIOU with the input of 0.5x scale, 3.61% higher than STDC-Seg.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 25 of its 29 references that are in the map. First posted on arXiv 10 May 2022.

Builds on

25 of 29 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2017Mask R-CNNcited by 7,259
  3. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  4. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  5. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  6. 2016Pyramid Scene Parsing Networkcited by 2,472
  7. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  8. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  9. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
  10. 2017Deformable Convolutional Networkscited by 1,481
  11. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,194
  12. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,054
13 more
  1. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
  2. 2015Holistically-Nested Edge Detectioncited by 590
  3. 2019EDVR: Video Restoration with Enhanced Deformable Convolutional Networkscited by 492
  4. 2019GhostNet: More Features from Cheap Operationscited by 410
  5. 2020BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentationcited by 294
  6. 2016ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentationcited by 291
  7. 2017ICNet for Real-Time Semantic Segmentation on High-Resolution Imagescited by 261
  8. 2020Hierarchical Multi-Scale Attention for Semantic Segmentationcited by 183
  9. 2021Rethinking BiSeNet For Real-time Semantic Segmentationcited by 124
  10. 2019DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentationcited by 100
  11. 2021FaPN: Feature-aligned Pyramid Network for Dense Image Predictioncited by 81
  12. 2017Real-time Semantic Image Segmentation via Spatial Sparsitycited by 6
  13. 2020LRNNet: A Light-Weighted Network with Efficient Reduced Non-Local Operation for Real-Time Semantic Segmentationcited by 5

Built on by

Not cited yet.