arXiv Machine Learning September 1, 2026 By Rahul Nair, Gabriel Tseng, Esther Rolf, Bhanu Tokas, Hannah Kerner

Classification Drives Geographic Bias in Street Scene Segmentation

Read the original on arXiv Machine Learning →

The Flow has not summarised this story yet — read it at arXiv Machine Learning.

arXiv Computer Vision

1d ago

GeoBiaset: A Counterfactual Benchmark for Demographic Bias in World-Level Geolocalization

GeoBiaset is a new benchmark that tests how world-level image geolocalization models react to the apparent race of a person inserted into the image foreground. The dataset contains 9,541 images, each paired with counterfactual edits across seven races while keeping the background and ground-truth coordinates unchanged. Experiments show that demographic perturbations can cause a 16–47% drop in continent-level accuracy, and that models shift their focus from geographic landmarks to facial features when landmarks are absent.

By Niccol\`o Niccoli, Silvia Dani, Marco Mistretta, Andrew D. Bagdanov, Marco Bertini, Lorenzo Seidenari

llms multimodal benchmarks safety

arXiv Computer Vision

Sep 15

GeoMetric: Injecting Metric Geographic Structure into Worldwide Image Geo-Localization

arXiv:2606.08918v2 Announce Type: replace Abstract: Worldwide image geo-localization aims to determine where on Earth a single image was captured. However, visually similar scenes may lie thousands o...

By Junchao Cui, Xuanzi Ma, Wenqi Shi, Nan Wu, Biru Zhu, Xiangyang Luo

llms rag multimodal benchmarks

Hugging Face Trending Papers

Jul 29

Object Detection for Autonomous Driving in Chinese Rural Scenes: An Experimental Study on Real-Synthetic Data Mixing and Model Evaluation

Currently, autonomous driving object detection models face significant data scarcity and generalization challenges when navigating complex Chinese rural traffic scenarios. To address these limitations, we propose a novel real-synthetic mixed object detection dataset tailored specifically for Chinese rural roads and systematically evaluate the performance of 13 mainstream detectors under different real-to-synthetic data ratios, thereby providing empirical evidence for model selection and data strategy design in rural autonomous driving scenarios.

agents computer-vision robotics

arXiv AI

Aug 25

What Does CLIP Learn for Regional Geolocalization? Probing Visual Cues and Scene Configuration After Adaptation

arXiv:2608.21761v1 Announce Type: new Abstract: Large collections of street-view imagery provide rich visual information about urban environments, but extracting fine-grained geographic information f...

By Changyu Lee, Yeonsoo Park, Abdullah Alfarrarjeh, Seon Ho Kim

fine-tuning

arXiv Machine Learning

Jun 4

An Open-Source Two-Stage Computer Vision Pipeline for Fine-Grained Vehicle Classification using Vision Transformers

arXiv:2606. 05149v1 Announce Type: cross Abstract: Vehicle body type is a significant determinant of cyclist injury severity in overtaking crashes, yet automated tools for classifying vehicles into injury-risk-relevant categories from naturalistic roadway video do not exist in the open literature.

By Gandhimathi Padmanaban, Fred Feng

llms computer-vision fine-tuning benchmarks safety

Hugging Face Trending Papers

Jul 30

Scaling Vision-Language Models Is Not Enough to Mitigate Bias

Vision-Language Models (VLMs) such as CLIP are now foundational to multimodal systems, yet their robustness to spurious correlations remains poorly understood at scale. We present the first large-scale empirical study of 194 publicly available VLMs, including 16 model families, covering a wide range of model sizes, 24 training datasets, and three evaluation benchmarks, namely ImageNet (overall performance), CelebA (typical single-attribute bias), and UrbanCars (complex multi-attribute biases).