Classification Drives Geographic Bias in Street Scene Segmentation

• URL: http://arxiv.org/abs/2412.11061v1
• Date: Sun, 15 Dec 2024 05:33:10 GMT
• Title: Classification Drives Geographic Bias in Street Scene Segmentation
• Authors: Rahul Nair, Gabriel Tseng, Esther Rolf, Bhanu Tokas, Hannah Kerner,
• Abstract summary: We investigated geo-biases in real-world driving datasets on a more complex task: instance segmentation.<n>We found that geo-biases came from classification errors rather than localization errors.<n>Our findings show that in region-specific models, geo-biases can be significantly mitigated by using coarser classes.
• Score: 20.14340857253721
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Previous studies showed that image datasets lacking geographic diversity can lead to biased performance in models trained on them. While earlier work studied general-purpose image datasets (e.g., ImageNet) and simple tasks like image recognition, we investigated geo-biases in real-world driving datasets on a more complex task: instance segmentation. We examined if instance segmentation models trained on European driving scenes (Eurocentric models) are geo-biased. Consistent with previous work, we found that Eurocentric models were geo-biased. Interestingly, we found that geo-biases came from classification errors rather than localization errors, with classification errors alone contributing 10-90% of the geo-biases in segmentation and 19-88% of the geo-biases in detection. This showed that while classification is geo-biased, localization (including detection and segmentation) is geographically robust. Our findings show that in region-specific models (e.g., Eurocentric models), geo-biases from classification errors can be significantly mitigated by using coarser classes (e.g., grouping car, bus, and truck as 4-wheeler).

Related papers

• GeoAgent: Learning to Geolocate Everywhere with Reinforced Geographic Characteristics [91.17301794848025]
  This paper presents GeoAgent, a model capable of reasoning closely with humans and deriving fine-grained address conclusions.<n>Previous RL-based methods have achieved breakthroughs in performance and interpretability but still remain concerns because of their reliance on AI-generated chain-of-thought (CoT) data and training strategies.
  arXiv  Detail & Related papers  (2026-02-13T04:48:05Z)
• Scaling Image Geo-Localization to Continent Level [48.7766435870634]
  This paper introduces a hybrid approach that achieves fine-grained geo-localization across a large geographic expanse the size of a continent.<n>We leverage a proxy classification task during training to learn rich feature representations that implicitly encode precise location information.<n>Our evaluation demonstrates that our approach can localize within 200m more than 68% of queries of a dataset covering a large part of Europe.
  arXiv  Detail & Related papers  (2025-10-30T17:59:35Z)
• GeoSURGE: Geo-localization using Semantic Fusion with Hierarchy of Geographic Embeddings [3.43519422766841]
  We formulate geo-localization as aligning the visual representation of the query image with a learned geographic representation.<n>Our main experiments demonstrate improved all-time bests in 22 out of 25 metrics measured across five benchmark datasets.
  arXiv  Detail & Related papers  (2025-10-01T20:39:48Z)
• GeoBS: Information-Theoretic Quantification of Geographic Bias in AI Models [34.611626290720295]
  We establish an information-theoretic framework for geo-bias evaluation, called GeoBS (Geo-Bias Scores)<n>We propose three novel geo-bias scores that explicitly take intricate spatial factors into consideration.
  arXiv  Detail & Related papers  (2025-09-27T20:07:21Z)
• Geolocation with Real Human Gameplay Data: A Large-Scale Dataset and Human-Like Reasoning Framework [59.42946541163632]
  We introduce a comprehensive geolocation framework with three key components. GeoComp, a large-scale dataset; GeoCoT, a novel reasoning method; and GeoEval, an evaluation metric. We demonstrate that GeoCoT significantly boosts geolocation accuracy by up to 25% while enhancing interpretability.
  arXiv  Detail & Related papers  (2025-02-19T14:21:25Z)
• Regional biases in image geolocation estimation: a case study with the SenseCity Africa dataset [0.0]
  We apply a state-of-the-art image geolocation estimation model (ISNs) to a crowd-sourced dataset of geolocated images from the African continent (SCA100) Our findings show that the ISNs model tends to over-predict image locations in high-income countries of the Western world. Our results suggest that using IM2GPS3k as a training set and benchmark for image geolocation estimation and other computer vision models overlooks its potential application in the African context.
  arXiv  Detail & Related papers  (2024-04-03T08:27:24Z)
• GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization [61.10806364001535]
  Worldwide Geo-localization aims to pinpoint the precise location of images taken anywhere on Earth. Existing approaches divide the globe into discrete geographic cells, transforming the problem into a classification task. We propose GeoCLIP, a novel CLIP-inspired Image-to-GPS retrieval approach that enforces alignment between the image and its corresponding GPS locations.
  arXiv  Detail & Related papers  (2023-09-27T20:54:56Z)
• PIGEON: Predicting Image Geolocations [44.99833362998488]
  We present a new geolocalization system that combines semantic geocell creation, multi-task contrastive pretraining, and a novel loss function. PIGEOTTO is the first image geolocalization model that effectively generalizes to unseen places.
  arXiv  Detail & Related papers  (2023-07-11T23:36:49Z)
• GeoGLUE: A GeoGraphic Language Understanding Evaluation Benchmark [56.08664336835741]
  We propose a GeoGraphic Language Understanding Evaluation benchmark, named GeoGLUE. We collect data from open-released geographic resources and introduce six natural language understanding tasks. We pro vide evaluation experiments and analysis of general baselines, indicating the effectiveness and significance of the GeoGLUE benchmark.
  arXiv  Detail & Related papers  (2023-05-11T03:21:56Z)
• GeoNet: Benchmarking Unsupervised Adaptation across Geographies [71.23141626803287]
  We study the problem of geographic robustness and make three main contributions. First, we introduce a large-scale dataset GeoNet for geographic adaptation. Second, we hypothesize that the major source of domain shifts arise from significant variations in scene context. Third, we conduct an extensive evaluation of several state-of-the-art unsupervised domain adaptation algorithms and architectures.
  arXiv  Detail & Related papers  (2023-03-27T17:59:34Z)
• GeoDE: a Geographically Diverse Evaluation Dataset for Object Recognition [31.194474203667042]
  GeoDE is a geographically diverse dataset with 61,940 images from 40 classes and 6 world regions. We release the full dataset and code at https://geodiverse-data-collection.cs.princeton.edu/.
  arXiv  Detail & Related papers  (2023-01-05T18:21:50Z)
• G^3: Geolocation via Guidebook Grounding [92.46774241823562]
  We study explicit knowledge from human-written guidebooks that describe the salient and class-discriminative visual features humans use for geolocation. We propose the task of Geolocation via Guidebook Grounding that uses a dataset of StreetView images from a diverse set of locations. Our approach substantially outperforms a state-of-the-art image-only geolocation method, with an improvement of over 5% in Top-1 accuracy.
  arXiv  Detail & Related papers  (2022-11-28T16:34:40Z)
• PGL: Prior-Guided Local Self-supervised Learning for 3D Medical Image Segmentation [87.50205728818601]
  We propose a PriorGuided Local (PGL) self-supervised model that learns the region-wise local consistency in the latent feature space. Our PGL model learns the distinctive representations of local regions, and hence is able to retain structural information.
  arXiv  Detail & Related papers  (2020-11-25T11:03:11Z)

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.