mlsanityData to 7 Oct 2026

Can domain adaptation make object recognition work for everyone?

arXiv 2204.11122 ↗First posted 23 Apr 2022cs.CV cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

Despite the rapid progress in deep visual recognition, modern computer vision datasets significantly overrepresent the developed world and models trained on such datasets underperform on images from unseen geographies. We investigate the effectiveness of unsupervised domain adaptation (UDA) of such models across geographies at closing this performance gap. To do so, we first curate two shifts from existing datasets to study the Geographical DA problem, and discover new challenges beyond data distribution shift: context shift, wherein object surroundings may change significantly across geographies, and subpopulation shift, wherein the intra-category distributions may shift. We demonstrate the inefficacy of standard DA methods at Geographical DA, highlighting the need for specialized geographical adaptation solutions to address the challenge of making object recognition work for everyone.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 23 of its 26 references that are in the map. First posted on arXiv 23 Apr 2022.

Builds on

23 of 26 references.

References · 23

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  5. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  6. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  7. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  8. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
  9. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  10. 2019A Closer Look at Few-shot Classificationcited by 679
  11. 2017Functional Map of the Worldcited by 338
  12. 2015YFCC100M: The New Data in Multimedia Researchcited by 234
11 more
  1. 2020BREEDS: Benchmarks for Subpopulation Shiftcited by 155
  2. 2017No Classification without Representation: Assessing Geodiversity Issues in Open Data Sets for the Developing Worldcited by 152
  3. 2020Train in Germany, Test in The USA: Making 3D Object Detectors Generalizecited by 150
  4. 2019Does Object Recognition Work for Everyone?cited by 149
  5. 2020Don't Judge an Object by Its Context: Learning to Overcome Contextual Biascited by 91
  6. 2021Extending the WILDS Benchmark for Unsupervised Adaptationcited by 85
  7. 2020SENTRY: Selective Entropy Optimization via Committee Consistency for Unsupervised Domain Adaptationcited by 78
  8. 2021Adaptive Methods for Real-World Domain Generalizationcited by 66
  9. 2020CASTing Your Model: Learning to Localize Improves Self-Supervised Representationscited by 63
  10. 2021A Theory of Label Propagation for Subpopulation Shiftcited by 48
  11. 2021Object-aware Contrastive Learning for Debiased Scene Representationcited by 34

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 5.

8 papers.

  1. 2023GeoNet: Benchmarking Unsupervised Adaptation across Geographiescited by 17
  2. 2023GIVL: Improving Geographical Inclusivity of Vision-Language Models with Pre-Training Methodscited by 11
  3. 2023Learning to Drive Anywherecited by 9
  4. 2024Incorporating Geo-Diverse Knowledge into Prompting for Increased Geographical Robustness in Object Recognitioncited by 4
  5. 2024We're Not Using Videos Effectively: An Updated Domain Adaptive Video Segmentation Baselinecited by 4
  6. 2024Tell, Don't Show!: Language Guidance Eases Transfer Across Domains in Images and Videoscited by 4
  7. 2024Dual Risk Minimization: Towards Next-Level Robustness in Fine-tuning Zero-Shot Modelscited by 2
  8. 2024Semantically Guided Action Anticipationcited by 0