← Back to all news
arXiv Machine Learning

Classification Drives Geographic Bias in Street Scene Segmentation

Related stories

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
llmsmultimodalbenchmarkssafety
More like this →
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.

agentscomputer-visionrobotics
More like this →
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
llmscomputer-visionfine-tuningbenchmarkssafety
More like this →
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).

llmsmultimodalbenchmarkssafety
More like this →
arXiv Computer Vision
Oct 2

Domain generalization and synthetic data in object detection: the enabler, the probe, and the gap

The paper reviews domain generalization (DG) for object detection, highlighting its scarcity and unique challenges such as localization and multi-scale representation. It examines synthetic data from three angles: as an enabler that diversifies and aligns training data, as a probe that allows controlled experiments to uncover failure modes, and as a source of a synthetic‑to‑real gap that hampers deployment on real imagery. The authors conclude that future DG research must develop representation‑aware methods that explicitly address both localization and classification under domain shift.

By Elfi I. S. Hofmeijer, Ella P. Fokkinga, Friso G. Heslinga, Klamer Schutte, J\"orgen M. Karlholm
computer-visionsafety
More like this →