mlsanityData to 7 Oct 2026

Neural Architecture Search for Dense Prediction Tasks in Computer Vision

arXiv 2202.07242 ↗First posted 15 Feb 2022cs.CV cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

The success of deep learning in recent years has lead to a rising demand for neural network architecture engineering. As a consequence, neural architecture search (NAS), which aims at automatically designing neural network architectures in a data-driven manner rather than manually, has evolved as a popular field of research. With the advent of weight sharing strategies across architectures, NAS has become applicable to a much wider range of problems. In particular, there are now many publications for dense prediction tasks in computer vision that require pixel-level predictions, such as semantic segmentation or object detection. These tasks come with novel challenges, such as higher memory footprints due to high-resolution data, learning multi-scale representations, longer training times, and more complex and larger neural architectures. In this manuscript, we provide an overview of NAS for dense prediction tasks by elaborating on these novel challenges and surveying ways to address them to ease future research and application of existing methods to novel problems.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 132 of its 172 references that are in the map. First posted on arXiv 15 Feb 2022.

Builds on

132 of 172 references.

References · 132

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  6. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  7. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  8. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  9. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  10. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  11. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  12. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
38 more
  1. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  2. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  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. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  7. 2015Fast R-CNNcited by 2,930
  8. 2016Pyramid Scene Parsing Networkcited by 2,472
  9. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  10. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  11. 2019Searching for MobileNetV3cited by 1,984
  12. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  13. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  14. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  15. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  16. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,194
  17. 2017A Survey on Deep Learning in Medical Image Analysiscited by 1,182
  18. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
  19. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,097
  20. 2017Deep Image Priorcited by 1,097
  21. 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,063
  22. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
  23. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,054
  24. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,018
  25. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 966
  26. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 937
  27. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  28. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 902
  29. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 878
  30. 2018Efficient Neural Architecture Search via Parameter Sharingcited by 831
  31. 2018SNIP: Single-shot Network Pruning based on Connection Sensitivitycited by 802
  32. 2018Path Aggregation Network for Instance Segmentationcited by 796
  33. 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 780
  34. 2014Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognitioncited by 719
  35. 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 666
  36. 2018FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Searchcited by 480
  37. 2018BOHB: Robust and Efficient Hyperparameter Optimization at Scalecited by 466
  38. 2020Searching Efficient 3D Architectures with Sparse Point-Voxel Convolutioncited by 422

50 most cited of 132 All 132 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 2; 2025: 3; 2026: 1.

11 papers.

  1. 2023Neural Architecture Search: Insights from 1000 Paperscited by 136
  2. 2023AmodalSynthDrive: A Synthetic Amodal Perception Dataset for Autonomous Drivingcited by 13
  3. 2023Syn-Mediverse: A Multimodal Synthetic Dataset for Intelligent Scene Understanding of Healthcare Facilitiescited by 10
  4. 2024Progressive Multi-Modal Fusion for Robust 3D Object Detectioncited by 10
  5. 2026ForecastOcc: Vision-based Semantic Occupancy Forecastingcited by 6
  6. 2025Open-Set LiDAR Panoptic Segmentation Guided by Uncertainty-Aware Learningcited by 5
  7. 2025Hyperspectral Adapter for Semantic Segmentation with Vision Foundation Modelscited by 5
  8. 2024Multi-Agents Based on Large Language Models for Knowledge-based Visual Question Answeringcited by 3
  9. 2025DeepCAVE: A Visualization and Analysis Tool for Automated Machine Learningcited by 2
  10. 2023Supervised and Contrastive Self-Supervised In-Domain Representation Learning for Dense Prediction Problems in Remote Sensingcited by 0
  11. 2023NAS-ASDet: An Adaptive Design Method for Surface Defect Detection Network using Neural Architecture Searchcited by 0