paper-with-me

홈 › Papers

Enhancing Contrastive Learning for Geolocalization by Discovering Hard Negatives on Semivariograms

2025-09-25 · Boyi Chen, Zhangyu Wang, Fabian Deuser, Johann Maximilian Zollner, Martin Werner arxiv

Accurate and robust image-based geo-localization at a global scale is challenging due to diverse environments, visually ambiguous scenes, and the lack of distinctive landmarks in many regions. While contrastive learning methods show promising performance by aligning features between street-view images and corresponding locations, they neglect the underlying spatial dependency in the geographic space. As a result, they fail to address the issue of false negatives -- image pairs that are both visually and geographically similar but labeled as negatives, and struggle to effectively distinguish hard negatives, which are visually similar but geographically distant. To address this issue, we propose a novel spatially regularized contrastive learning strategy that integrates a semivariogram, which is a geostatistical tool for modeling how spatial correlation changes with distance. We fit the semivariogram by relating the distance of images in feature space to their geographical distance, capturing the expected visual content in a spatial correlation. With the fitted semivariogram, we define the expected visual dissimilarity at a given spatial distance as reference to identify hard negatives and false negatives. We integrate this strategy into GeoCLIP and evaluate it on the OSV5M dataset, demonstrating that explicitly modeling spatial priors improves image-based geo-localization performance, particularly at finer granularity.

📄 PDF Abstract BibTeX arXiv:2509.21573

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive Learning

Similar Papers 제목 키워드 기반

SynCo: Synthetic Hard Negatives in Contrastive Learning for Better Unsupervised Visual Representations

2024-10-03 · Nikolaos Giakoumoglou, Tania Stathaki

Contrastive learning has become a dominant approach in self-supervised visual representation learning. Hard negatives - samples closely resembling the anchor - are key to enhancing learned representations' discriminative…

Contrastive LearningImage ClassificationImage SegmentationInstance Segmentation+8

Future Sight and Tough Fights: Revolutionizing Sequential Recommendation with FENRec

2024-12-16 · Yu-Hsuan Huang, Ling Lo, HongXia Xie, Hong-Han Shuai 외

Sequential recommendation (SR) systems predict user preferences by analyzing time-ordered interaction sequences. A common challenge for SR is data sparsity, as users typically interact with only a limited number of items…

Contrastive LearningSequential Recommendation

Khan-GCL: Kolmogorov-Arnold Network Based Graph Contrastive Learning with Hard Negatives

2025-05-21 · Zihu Wang, Boxun Xu, Hejia Geng, Peng Li

Graph contrastive learning (GCL) has demonstrated great promise for learning generalizable graph representations from unlabeled data. However, conventional GCL approaches face two critical limitations: (1) the restricted…

Contrastive Learning

Visual Perturbation and Adaptive Hard Negative Contrastive Learning for Compositional Reasoning in Vision-Language Models

2025-05-21 · Xin Huang, Ruibin Li, Tong Jia, Wei Zheng 외

Vision-Language Models (VLMs) are essential for multimodal tasks, especially compositional reasoning (CR) tasks, which require distinguishing fine-grained semantic differences between visual and textual embeddings. Howev…

Contrastive Learning

Understanding Hard Negatives in Noise Contrastive Estimation

2021-04-13 · NAACL 2021 4 · Wenzheng Zhang, Karl Stratos

The choice of negative examples is important in noise contrastive estimation. Recent works find that hard negatives -- highest-scoring incorrect examples under the model -- are effective in practice, but they are used wi…

Entity LinkingRetrievalText Retrieval