paper-with-me

홈 › Papers

Are Local Features All You Need for Cross-Domain Visual Place Recognition?

2023-04-12 · Giovanni Barbarani, Mohamad Mostafa, Hajali Bayramov, Gabriele Trivigno, Gabriele Berton, Carlo Masone, Barbara Caputo

Visual Place Recognition is a task that aims to predict the coordinates of an image (called query) based solely on visual clues. Most commonly, a retrieval approach is adopted, where the query is matched to the most similar images from a large database of geotagged photos, using learned global descriptors. Despite recent advances, recognizing the same place when the query comes from a significantly different distribution is still a major hurdle for state of the art retrieval methods. Examples are heavy illumination changes (e.g. night-time images) or substantial occlusions (e.g. transient objects). In this work we explore whether re-ranking methods based on spatial verification can tackle these challenges, following the intuition that local descriptors are inherently more robust than global features to domain shifts. To this end, we provide a new, comprehensive benchmark on current state of the art models. We also introduce two new demanding datasets with night and occluded queries, to be matched against a city-wide database. Code and datasets are available at https://github.com/gbarbarani/re-ranking-for-VPR.

📄 PDF Abstract BibTeX arXiv:2304.05887

Code (1)

gbarbarani/re-ranking-for-vpr 공식 구현 pytorch

Tasks

AllRe-RankingRetrievalVisual Place Recognition

Similar Papers 제목 키워드 기반

Domain Adaptation of Learned Features for Visual Localization

2020-08-21 · Sungyong Baik, Hyo Jin Kim, Tianwei Shen, Eddy Ilg 외

We tackle the problem of visual localization under changing conditions, such as time of day, weather, and seasons. Recent learned local features based on deep neural networks have shown superior performance over classica…

Domain AdaptationVisual Localization

Interpretable Cross-Domain Few-Shot Learning with Rectified Target-Domain Local Alignment

2026-03-18 · Yaze Zhao, Yixiong Zou, Yuhua Li, Ruixuan Li arxiv

Cross-Domain Few-Shot Learning (CDFSL) adapts models trained with large-scale general data (source domain) to downstream target domains with only scarce training data, where the research on vision-language models (e.g., …

cross-domain few-shot learningMedical Diagnosis

VLAD-VSA: Cross-Domain Face Presentation Attack Detection with Vocabulary Separation and Adaptation

2022-02-21 · Jiong Wang, Zhou Zhao, Weike Jin, Xinyu Duan 외

For face presentation attack detection (PAD), most of the spoofing cues are subtle, local image patterns (e.g., local image distortion, 3D mask edge and cut photo edges). The representations of existing PAD works with si…

DiversityFace Presentation Attack Detection

Long-Term Invariant Local Features via Implicit Cross-Domain Correspondences

2023-11-06 · Zador Pataki, Mohammad Altillawi, Menelaos Kanakis, Rémi Pautrat 외

Modern learning-based visual feature extraction networks perform well in intra-domain localization, however, their performance significantly declines when image pairs are captured across long-term visual domain variation…

Visual Localization

Vision Transformer-Conditioned UNet for Domain-Adaptive Semantic Segmentation

2026-05-12 · Joel Valdivia Ortega, Tingying Peng, Marion Jasnin arxiv

Semantic segmentation is essential for analysing anatomical features in biomedical research, yet a performance gap remains for Vision Transformers (ViTs) in the field, particularly for sparse, fine-structured, and low si…

Semantic Segmentation