Classification for everyone : Building geography agnostic models for fairer recognition

• URL: http://arxiv.org/abs/2312.02957v3
• Date: Tue, 2 Apr 2024 05:12:10 GMT
• Title: Classification for everyone : Building geography agnostic models for fairer recognition
• Authors: Akshat Jindal, Shreya Singh, Soham Gadgil,
• Abstract summary: We quantitatively present this bias in two datasets - The Dollar Street dataset and ImageNet. We then present different methods which can be employed to reduce this bias.
• Score: 0.9558392439655016
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Application of Disentanglement to Map Registration Problem [0.3277163122167434]
  It is essential to first align different "styles" of geospatial data to its matching images that point to the same location on the surface of the Earth. We propose a combination of $beta$-VAE-like architecture and adversarial training to achieve both the disentanglement of the geographic information and artistic styles and generation of new map tiles.
  arXiv  Detail & Related papers  (2024-08-26T09:55:32Z)
• Reinforcing Pre-trained Models Using Counterfactual Images [54.26310919385808]
  This paper proposes a novel framework to reinforce classification models using language-guided generated counterfactual images. We identify model weaknesses by testing the model using the counterfactual image dataset. We employ the counterfactual images as an augmented dataset to fine-tune and reinforce the classification model.
  arXiv  Detail & Related papers  (2024-06-19T08:07:14Z)
• Decomposed evaluations of geographic disparities in text-to-image models [22.491466809896867]
  We introduce a new set of metrics, Decomposed Indicators of Disparities in Image Generation (Decomposed-DIG), that allows us to measure geographic disparities in the depiction of objects and backgrounds in generated images. Using Decomposed-DIG, we audit a widely used latent diffusion model and find that generated images depict objects with better realism than backgrounds. We use Decomposed-DIG to pinpoint specific examples of disparities, such as stereotypical background generation in Africa, struggling to generate modern vehicles in Africa, and unrealistically placing some objects in outdoor settings.
  arXiv  Detail & Related papers  (2024-06-17T18:04:23Z)
• Classifying geospatial objects from multiview aerial imagery using semantic meshes [2.116528763953217]
  We propose a new method to predict tree species based on aerial images of forests in the U.S. We show that our proposed multiview method improves classification accuracy from 53% to 75% relative to an orthoorthoaic baseline on a challenging cross-site tree classification task.
  arXiv  Detail & Related papers  (2024-05-15T17:56:49Z)
• Mitigating Bias Using Model-Agnostic Data Attribution [2.9868610316099335]
  Mitigating bias in machine learning models is a critical endeavor for ensuring fairness and equity. We propose a novel approach to address bias by leveraging pixel image attributions to identify and regularize regions of images containing bias attributes.
  arXiv  Detail & Related papers  (2024-05-08T13:00:56Z)
• Enhance Image Classification via Inter-Class Image Mixup with Diffusion Model [80.61157097223058]
  A prevalent strategy to bolster image classification performance is through augmenting the training set with synthetic images generated by T2I models. In this study, we scrutinize the shortcomings of both current generative and conventional data augmentation techniques. We introduce an innovative inter-class data augmentation method known as Diff-Mix, which enriches the dataset by performing image translations between classes.
  arXiv  Detail & Related papers  (2024-03-28T17:23:45Z)
• Uncovering the Background-Induced bias in RGB based 6-DoF Object Pose Estimation [5.30320006562872]
  In recent years, there has been a growing trend of using data-driven methods in industrial settings. It becomes critical to understand how the manipulation of video and images can impact the effectiveness of a machine learning method. Our case study aims precisely to analyze the Linemod dataset, considered the state of the art in 6D pose estimation context.
  arXiv  Detail & Related papers  (2023-04-17T12:54:20Z)
• Where We Are and What We're Looking At: Query Based Worldwide Image Geo-localization Using Hierarchies and Scenes [53.53712888703834]
  We introduce an end-to-end transformer-based architecture that exploits the relationship between different geographic levels. We achieve state of the art street level accuracy on 4 standard geo-localization datasets.
  arXiv  Detail & Related papers  (2023-03-07T21:47:58Z)
• Activation Regression for Continuous Domain Generalization with Applications to Crop Classification [48.795866501365694]
  Geographic variance in satellite imagery impacts the ability of machine learning models to generalise to new regions. We model geographic generalisation in medium resolution Landsat-8 satellite imagery as a continuous domain adaptation problem. We develop a dataset spatially distributed across the entire continental United States.
  arXiv  Detail & Related papers  (2022-04-14T15:41:39Z)
• Unravelling the Effect of Image Distortions for Biased Prediction of Pre-trained Face Recognition Models [86.79402670904338]
  We evaluate the performance of four state-of-the-art deep face recognition models in the presence of image distortions. We have observed that image distortions have a relationship with the performance gap of the model across different subgroups.
  arXiv  Detail & Related papers  (2021-08-14T16:49:05Z)
• Geo-Spatiotemporal Features and Shape-Based Prior Knowledge for Fine-grained Imbalanced Data Classification [63.916371837696396]
  Fine-grained classification aims at distinguishing between items with similar global perception and patterns, but that differ by minute details. Our primary challenges come from both small inter-class variations and large intra-class variations. We propose to combine several innovations to improve fine-grained classification within the use-case of wildlife.
  arXiv  Detail & Related papers  (2021-03-21T02:01:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.