Bridging Geographic Bias in Urban Streetscape Inference via Lifelong Learning with Visual-Semantic Pivoting

• URL: http://arxiv.org/abs/2606.15055v1
• Date: Sat, 13 Jun 2026 01:52:03 GMT
• Title: Bridging Geographic Bias in Urban Streetscape Inference via Lifelong Learning with Visual-Semantic Pivoting
• Abstract summary: Visual perception of urban streetscapes underpins evidence-based decisions in landscape planning, public health, and place-making.<n>Yet models trained on a few well-photographed metropolises systematically misjudge underrepresented districts.<n>We address this gap with HVSP-LL, a lifelong learning framework that couples a visual-semantic pivoting module with an equity-aware rehearsal mechanism.
• Score: 2.538209532048867
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Visual perception of urban streetscapes underpins evidence-based decisions in landscape planning, public health, and place-making. Yet models trained on a few well-photographed metropolises systematically misjudge underrepresented districts, propagating geographic bias into downstream policy. We address this gap with HVSP-LL, a lifelong learning framework that couples a stratified visual-semantic pivoting module with an equity-aware rehearsal mechanism. The pivoting module organises landscape concepts along a three-tier ontology (macro structure, meso composition, micro element) and aligns image features to learnable semantic anchors at each tier, providing transferable representations that resist distributional drift. The lifelong adaptation component sequentially absorbs new urban regions while constraining inter-region perception gaps through a worst-region sample-reweighting objective and a structurally-aware exemplar buffer. We evaluate HVSP-LL on a panoramic streetscape benchmark assembled from twelve cities across four continents and seven perceptual dimensions. The framework attains 0.834 Spearman correlation on the held-out city sequence, an absolute 6.1 point improvement over the strongest continual baseline, and shrinks the inter-city perception gap to 0.094 -- a 38% reduction relative to the strongest continual baseline (0.151) and a 57% reduction relative to a representative regularisation baseline (0.218). Ablations confirm that each tier of the pivoting hierarchy contributes monotonically, and the equity-aware rehearsal converts mean backward transfer from -0.038 (without retention) to +0.013, eliminating catastrophic forgetting on the held-out sequence. Our results indicate that hierarchical anchoring is a practical pathway toward geographically equitable streetscape inference at city scale.

Related papers

• Cross-View Urban Sensing: Mapping Subjective Streetscape Perception via AlphaEarth Embeddings and Urban Context [14.193542027484213]
  We present CVLNet, a Cross-View Learning Network that predicts street-level perception without requiring SVI at inference.<n>CVLNet is evaluated across four Southeast Asian cities: Singapore, Kuala Lumpur, Jakarta, and Manila.<n>We produce citywide road-level streetscape perception maps for five subjective perceptual dimensions across all four cities.
  arXiv  Detail & Related papers  (2026-08-17T09:21:30Z)
• Lost in the Tail: Addressing Geographic Imbalance in Urban Visual Place Recognition [9.31929142038003]
  Urban-scale Visual Place Recognition aims to identify the geographic location of a query image by matching it against a geo-tagged database.<n>Recent methods achieve impressive performance, but overlook a serious long-tailed problem hidden in urban-scale datasets.<n>We propose Distribution-Aware Place Recognition (DAPR), a model-agnostic plug-in framework that rebalances gradient contributions across head and tail classes.
  arXiv  Detail & Related papers  (2026-06-30T19:33:39Z)
• SemCityLoc: Aerial 6DoF Localization Using Semantic 3D City Models [51.121529170856064]
  We propose SemCityLoc, a semantic-geometric alignment system that reframes aerial pose estimation.<n>Instead of matching sparse contours or dense texture, our method aligns semantic surfaces and monocular depth with lightweight semantic 3D building models.<n>Experiments demonstrate substantial improvements over existing map-based approaches.
  arXiv  Detail & Related papers  (2026-06-25T18:13:39Z)
• Hierarchical Consistency Learning for Test-time Adaptation in Camouflage Perception [50.278200968044665]
  Camouflaged object detection (COD) aims to localize targets that exhibit minimal perceptual differences from backgrounds through physical attributes.<n>Existing methods, constrained by the static train-then-freeze paradigm, suffer from domain rigidity and dependency annotation.<n>We propose the hierarchical consistency learning framework, which integrates test-time adaptation for dynamic representation recalibration.
  arXiv  Detail & Related papers  (2026-05-25T09:57:46Z)
• Beyond Localization: A Comprehensive Diagnosis of Perspective-Conditioned Spatial Reasoning in MLLMs from Omnidirectional Images [52.50752250573993]
  Multimodal Large Language Models (MLLMs) show strong visual perception, yet remain limited in reasoning about space under changing viewpoints.<n>We study this challenge as Perspective-Conditioned Spatial Reasoning (PCSR) in 360-degree omnidirectional images.<n>We introduce PCSR-Bench, a diagnostic benchmark of 84,373 question-answer pairs from 2,600 omnidirectional images.
  arXiv  Detail & Related papers  (2026-05-12T17:11:17Z)
• Slum Detection and Density Mapping with AlphaEarth Foundations: A Representation Learning Evaluation Across 12 Global Cities [9.982796078979648]
  Pixel-level slum mapping has long been constrained by limited cross-city generalisation.<n>AlphaEarth Foundations offers a new analysis-ready basis for lightweight slum monitoring.<n>We evaluate AEF on slum classification and sub-pixel density estimation across 12 cities and 69 city-year pairs.
  arXiv  Detail & Related papers  (2026-05-11T05:54:15Z)
• Can Attribution Predict Risk? From Multi-View Attribution to Planning Risk Signals in End-to-End Autonomous Driving [51.726472686971896]
  End-to-end autonomous driving models generate future trajectories from multi-view inputs.<n> Existing methods fail to reveal the visual evidence underlying trajectory generation.<n>We propose a hierarchical attribution framework for end-to-end planning.
  arXiv  Detail & Related papers  (2026-05-07T13:38:18Z)
• Earth Embeddings Reveal Diverse Urban Signals from Space [17.134313498337804]
  We benchmark three Earth embedding families, AlphaEarth, Prithvi, and Clay, for urban signal prediction.<n>Using a unified supervised-learning framework, we predict 14 neighborhood-level indicators spanning crime, income, health, and travel behavior.<n>Results show that Earth embeddings capture substantial urban variation, with the highest predictive skill for outcomes tied to built-environment structure.
  arXiv  Detail & Related papers  (2026-04-03T20:58:37Z)
• SLUM-i: Semi-supervised Learning for Urban Mapping of Informal Settlements and Data Quality Benchmarking [5.931174898048042]
  Rapid urban expansion has fueled the growth of informal settlements in major cities of low- and middle-income countries.<n>We introduce a benchmark dataset for Lahore, constructed from scratch, along with companion datasets for Karachi and Mumbai.<n>We propose a new semi-supervised segmentation framework designed to mitigate the class imbalance and feature degradation inherent in standard semi-supervised learning pipelines.
  arXiv  Detail & Related papers  (2026-02-04T13:16:30Z)
• VisitHGNN: Heterogeneous Graph Neural Networks for Modeling Point-of-Interest Visit Patterns [3.545082819007165]
  VisitHGNN is a relation-specific graph network designed to predict probabilities of individual Points of interest (POIs)<n>VisitHGNN achieves strong predictive performance with mean KL divergence of 0.287, MAE of 0.008, Top-1 accuracy of 0.853, and R-square of 0.853.<n>Model's potential for decision support in urban planning, transportation policy, mobility system, and public health.
  arXiv  Detail & Related papers  (2025-10-03T03:42:58Z)
• Interpretable Multimodal Framework for Human-Centered Street Assessment: Integrating Visual-Language Models for Perceptual Urban Diagnostics [0.0]
  This study introduces a novel Multimodal Street Evaluation Framework (MSEF)<n>We fine-tune the framework using LoRA and P-Tuning v2 for parameter-efficient adaptation.<n>The model achieves an F1 score of 0.84 on objective features and 89.3 percent agreement with aggregated resident perceptions.
  arXiv  Detail & Related papers  (2025-06-05T14:34:04Z)
• LoLep: Single-View View Synthesis with Locally-Learned Planes and Self-Attention Occlusion Inference [66.45326873274908]
  We propose a novel method, LoLep, which regresses Locally-Learned planes from a single RGB image to represent scenes accurately. Compared to MINE, our approach has an LPIPS reduction of 4.8%-9.0% and an RV reduction of 73.9%-83.5%.
  arXiv  Detail & Related papers  (2023-07-23T03:38:55Z)
• Consistency-Aware Anchor Pyramid Network for Crowd Localization [167.93943981468348]
  Crowd localization aims to predict the spatial position of humans in a crowd scenario. We propose an anchor pyramid scheme to adaptively determine the anchor density in each image region.
  arXiv  Detail & Related papers  (2022-12-08T04:32:01Z)

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.