GeoBiaset: A Counterfactual Benchmark for Demographic Bias in World-Level Geolocalization
cs.CV
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/miccunifi/GeoBiaset
Terminology
Sources
- Quality-Aware Image-Text Alignment for Opinion-Unaware Image Quality Assessment
- Measuring Social Bias in Vision-Language Models with Face-Only Counterfactuals from Real Photos
- FairerCLIP: Debiasing CLIP's Zero-Shot Predictions using Functions in RKHSs
- GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
- Uncovering Bias in Large Vision-Language Models with Counterfactuals
- Cultural Counterfactuals: Evaluating Cultural Biases in Large Vision-Language Models with Counterfactual Examples
- Evaluating Precise Geolocation Inference Capabilities of Vision Language Models
- GeoRanker: Distance-Aware Ranking for Worldwide Image Geolocalization
- FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age
- From Pixels to Places: A Systematic Benchmark for Evaluating Image Geolocalization Ability in Large Language Models
- DeepSeek-VL: Towards Real-World Vision-Language Understanding
- Where on Earth? A Vision-Language Benchmark for Probing Model Geolocation Skills Across Scales
- CounterFace: A Synthetic Face Dataset for Fine-Grained Counterfactual Evaluation of Face Recognition Systems
- GeoRC: A Benchmark for Geolocation Reasoning Chains
- Regional biases in image geolocation estimation: a case study with the SenseCity Africa dataset
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
- GeoCloak: An Agentic Framework for Semantics-Preserving Geolocation Privacy via Peripheral Clue Manipulation
- Qwen3 Technical Report
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs