mlsanityData to 7 Oct 2026

A benchmark with decomposed distribution shifts for 360 monocular depth estimation

arXiv 2112.00432 ↗First posted 1 Dec 2021cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

In this work we contribute a distribution shift benchmark for a computer vision task; monocular depth estimation. Our differentiation is the decomposition of the wider distribution shift of uncontrolled testing on in-the-wild data, to three distinct distribution shifts. Specifically, we generate data via synthesis and analyze them to produce covariate (color input), prior (depth output) and concept (their relationship) distribution shifts. We also synthesize combinations and show how each one is indeed a different challenge to address, as stacking them produces increased performance drops and cannot be addressed horizontally using standard approaches.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 26 references that are in the map. First posted on arXiv 1 Dec 2021.

Builds on

23 of 26 references.

References · 23

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  4. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  5. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  6. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,354
  7. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  8. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  9. 2017Progressive Neural Architecture Searchcited by 483
  10. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  11. 2019Enforcing geometric constraints of virtual normal for depth predictioncited by 233
  12. 2021A Fine-Grained Analysis on Distribution Shiftcited by 171
11 more
  1. 2018Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundariescited by 144
  2. 2018Evaluation of CNN-based Single-Image Depth Estimation Methodscited by 137
  3. 2019Interactive Gibson Benchmark (iGibson 0.5): A Benchmark for Interactive Navigation in Cluttered Environmentscited by 89
  4. 2021The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuningcited by 74
  5. 2021Adaptive Methods for Real-World Domain Generalizationcited by 66
  6. 2021Pano3D: A Holistic Benchmark and a Solid Baseline for 360o Depth Estimationcited by 37
  7. 2021On the Out-of-distribution Generalization of Probabilistic Image Modellingcited by 32
  8. 2019A Closer Look at Domain Shift for Deep Learning in Histopathologycited by 25
  9. 2021An Information-theoretic Approach to Distribution Shiftscited by 25
  10. 2021Towards a theory of out-of-distribution learningcited by 11
  11. 2021Understanding and Testing Generalization of Deep Networks on Out-of-Distribution Datacited by 5

Built on by

Not cited yet.