mlsanityData to 7 Oct 2026

Lightweight Monocular Depth with a Novel Neural Architecture Search Method

arXiv 2108.11105 ↗First posted 25 Aug 2021cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

This paper presents a novel neural architecture search method, called LiDNAS, for generating lightweight monocular depth estimation models. Unlike previous neural architecture search (NAS) approaches, where finding optimized networks are computationally highly demanding, the introduced novel Assisted Tabu Search leads to efficient architecture exploration. Moreover, we construct the search space on a pre-defined backbone network to balance layer diversity and search space size. The LiDNAS method outperforms the state-of-the-art NAS approach, proposed for disparity and depth estimation, in terms of search efficiency and output model performance. The LiDNAS optimized models achieve results superior to compact depth estimation state-of-the-art on NYU-Depth-v2, KITTI, and ScanNet, while being 7%-500% more compact in size, i.e the number of model parameters.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 86 of its 117 references that are in the map. First posted on arXiv 25 Aug 2021.

Builds on

86 of 117 references.

References · 86

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  3. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  5. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  6. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  7. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  8. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  9. 2016Pyramid Scene Parsing Networkcited by 2,472
  10. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  11. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  12. 2019Searching for MobileNetV3cited by 1,984
38 more
  1. 2021Vision Transformers for Dense Predictioncited by 1,789
  2. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  3. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  4. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
  5. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  6. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  7. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,256
  8. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  9. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,097
  10. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 966
  11. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 937
  12. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 902
  13. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 902
  14. 2016COCO-Stuff: Thing and Stuff Classes in Contextcited by 858
  15. 2018Efficient Neural Architecture Search via Parameter Sharingcited by 831
  16. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
  17. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
  18. 2020AdaBins: Depth Estimation using Adaptive Binscited by 596
  19. 2014Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFscited by 552
  20. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  21. 2017Progressive Neural Architecture Searchcited by 483
  22. 2018FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Searchcited by 480
  23. 2017Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolutioncited by 452
  24. 2019GhostNet: More Features from Cheap Operationscited by 410
  25. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 402
  26. 2016Accelerating the Super-Resolution Convolutional Neural Networkcited by 393
  27. 2019From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimationcited by 379
  28. 2016Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescuecited by 368
  29. 2015Learning Deconvolution Network for Semantic Segmentationcited by 365
  30. 2020BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentationcited by 294
  31. 2016Designing Neural Network Architectures using Reinforcement Learningcited by 277
  32. 2018Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Networkcited by 263
  33. 2017ICNet for Real-Time Semantic Segmentation on High-Resolution Imagescited by 261
  34. 2017MemNet: A Persistent Memory Network for Image Restorationcited by 244
  35. 2020Neural Architecture Search without Trainingcited by 241
  36. 2015BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentationcited by 238
  37. 2019Enforcing geometric constraints of virtual normal for depth predictioncited by 233
  38. 2019Lightweight Image Super-Resolution with Information Multi-distillation Networkcited by 227

50 most cited of 86 All 86 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 2; 2024: 1; 2025: 1.

6 papers.

  1. 2022Deep Depth Completion from Extremely Sparse Data: A Surveycited by 33
  2. 2024The Third Monocular Depth Estimation Challengecited by 10
  3. 2025The Fourth Monocular Depth Estimation Challengecited by 8
  4. 2022Fast Neural Architecture Search for Lightweight Dense Prediction Networkscited by 0
  5. 2023A Survey on Multi-Objective Neural Architecture Searchcited by 0
  6. 2023NAS-ASDet: An Adaptive Design Method for Surface Defect Detection Network using Neural Architecture Searchcited by 0