Are Local Features All You Need for Cross-Domain Visual Place Recognition?
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.
Code (1)
Tasks
AllRe-RankingRetrievalVisual Place RecognitionSimilar Papers 제목 키워드 기반
Domain Adaptation of Learned Features for Visual Localization
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 LocalizationInterpretable Cross-Domain Few-Shot Learning with Rectified Target-Domain Local Alignment
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 DiagnosisVLAD-VSA: Cross-Domain Face Presentation Attack Detection with Vocabulary Separation and Adaptation
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 DetectionLong-Term Invariant Local Features via Implicit Cross-Domain Correspondences
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 LocalizationVision Transformer-Conditioned UNet for Domain-Adaptive Semantic Segmentation
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