mlsanityData to 14 Oct 2026

Classification for everyone : Building geography agnostic models for fairer recognition

arXiv 2312.02957 ↗First posted 5 Dec 2023cs.CV cs.AI cs.CYcited by 5

Not on the map. Why?

Abstract (arXiv)

In this paper, we analyze different methods to mitigate inherent geographical biases present in state of the art image classification models. We first quantitatively present this bias in two datasets - The Dollar Street Dataset and ImageNet, using images with location information. We then present different methods which can be employed to reduce this bias. Finally, we analyze the effectiveness of the different techniques on making these models more robust to geographical locations of the images.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 9 of its 23 references that are in the map. First posted on arXiv 5 Dec 2023.

Builds on

9 of 23 references.

References · 9

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  5. 2017Adversarial Discriminative Domain Adaptationcited by 1,311
  6. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,082
  7. 2019Does Object Recognition Work for Everyone?cited by 151
  8. 2018Footwear Size Recommendation Systemcited by 10
  9. 2019One Embedding To Do Them Allcited by 10

Built on by

Cited by year

Citing papers per year: 2023: 4; 2024: 1.

5 papers.

  1. 2023Shaping Political Discourse using multi-source News Summarizationcited by 5
  2. 2023Exploring Graph Based Approaches for Author Name Disambiguationcited by 4
  3. 2024Zero-shot Active Learning Using Self Supervised Learningcited by 1
  4. 2023Detecting anxiety from short clips of free-form speechcited by 0
  5. 2023Exploring intra-task relations to improve meta-learning algorithmscited by 0