Cross-Domain Image Matching with Deep Feature Maps
We investigate the problem of automatically determining what type of shoe left an impression found at a crime scene. This recognition problem is made difficult by the variability in types of crime scene evidence (ranging from traces of dust or oil on hard surfaces to impressions made in soil) and the lack of comprehensive databases of shoe outsole tread patterns. We find that mid-level features extracted by pre-trained convolutional neural nets are surprisingly effective descriptors for this specialized domains. However, the choice of similarity measure for matching exemplars to a query image is essential to good performance. For matching multi-channel deep features, we propose the use of multi-channel normalized cross-correlation and analyze its effectiveness. Our proposed metric significantly improves performance in matching crime scene shoeprints to laboratory test impressions. We also show its effectiveness in other cross-domain image retrieval problems: matching facade images to segmentation labels and aerial photos to map images. Finally, we introduce a discriminatively trained variant and fine-tune our system through our proposed metric, obtaining state-of-the-art performance.
Code (1)
Tasks
Image RetrievalRetrievalSimilar Papers 제목 키워드 기반
Densely Semantic Enhancement for Domain Adaptive Region-free Detectors
Unsupervised domain adaptive object detection aims to adapt a well-trained detector from its original source domain with rich labeled data to a new target domain with unlabeled data. Previous works focus on improving the…
object-detectionObject DetectionRegion ProposalCross-Domain Few-Shot Semantic Segmentation via Doubly Matching Transformation
Cross-Domain Few-shot Semantic Segmentation (CD-FSS) aims to train generalized models that can segment classes from different domains with a few labeled images. Previous works have proven the effectiveness of feature tra…
Cross-Domain Few-ShotFew-Shot Semantic SegmentationSemantic SegmentationConDL: Detector-Free Dense Image Matching
In this work, we introduce a deep-learning framework designed for estimating dense image correspondences. Our fully convolutional model generates dense feature maps for images, where each pixel is associated with a descr…
Contrastive LearningSemi-supervised Multiscale Matching for SAR-Optical Image
Driven by the complementary nature of optical and synthetic aperture radar (SAR) images, SAR-optical image matching has garnered significant interest. Most existing SAR-optical image matching methods aim to capture effec…
Image MatchingInterpretable and Generalizable Person Re-Identification with Query-Adaptive Convolution and Temporal Lifting
For person re-identification, existing deep networks often focus on representation learning. However, without transfer learning, the learned model is fixed as is, which is not adaptable for handling various unseen scenar…
Domain GeneralizationGeneralizable Person Re-identificationMetric LearningPerson Re-Identification+1