mlsanityData to 14 Oct 2026

MOSAIC: Mobile Segmentation via decoding Aggregated Information and encoded Context

arXiv 2112.11623 ↗First posted 22 Dec 2021cs.CV cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

We present a next-generation neural network architecture, MOSAIC, for efficient and accurate semantic image segmentation on mobile devices. MOSAIC is designed using commonly supported neural operations by diverse mobile hardware platforms for flexible deployment across various mobile platforms. With a simple asymmetric encoder-decoder structure which consists of an efficient multi-scale context encoder and a light-weight hybrid decoder to recover spatial details from aggregated information, MOSAIC achieves new state-of-the-art performance while balancing accuracy and computational cost. Deployed on top of a tailored feature extraction backbone based on a searched classification network, MOSAIC achieves a 5% absolute accuracy gain surpassing the current industry standard MLPerf models and state-of-the-art architectures.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 25 of its 28 references that are in the map. First posted on arXiv 22 Dec 2021.

Builds on

25 of 28 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  4. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  5. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  6. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  7. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  8. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  9. 2016Pyramid Scene Parsing Networkcited by 2,479
  10. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,332
  11. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
  12. 2019Searching for MobileNetV3cited by 1,994
13 more
  1. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,487
  2. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,200
  3. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 943
  4. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 915
  5. 2014Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognitioncited by 720
  6. 2015Learning Deconvolution Network for Semantic Segmentationcited by 365
  7. 2016ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentationcited by 291
  8. 2017ICNet for Real-Time Semantic Segmentation on High-Resolution Imagescited by 261
  9. 2018ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentationcited by 133
  10. 2017CondenseNet: An Efficient DenseNet using Learned Group Convolutionscited by 122
  11. 2019DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentationcited by 100
  12. 2017Not All Pixels Are Equal: Difficulty-aware Semantic Segmentation via Deep Layer Cascadecited by 53
  13. 2020Discovering Multi-Hardware Mobile Models via Architecture Searchcited by 12

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 0; 2025: 1.

2 papers.

  1. 2023MaskConver: Revisiting Pure Convolution Model for Panoptic Segmentationcited by 4
  2. 2025Puzzle: Scheduling Multiple Deep Learning Models on Mobile Device with Heterogeneous Processorscited by 0