VeriCam: A Verification Baseline for the Classification of Unknown Data
2026-08-31 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors propose VeriCam, a method that improves how computers tell apart very similar images from new, unseen classes, especially in hard real-world tasks like reading license plates from different cameras. They train a model to learn detailed differences by comparing pairs of images and then group them using graph clustering techniques. Their approach helps overcome biases caused by different capture devices and performs well on a traffic surveillance dataset. This helps create fairer benchmarks for tasks like optical character recognition (OCR) on license plates.
Foundation modelsZero-shot classificationVerification taskRelational graphGraph clusteringLeiden algorithmCapture device biasLicense Plate recognitionOptical Character Recognition (OCR)F1-Score
Authors
Lucas Wojcik, Gabriel E. Lima, Sergio M. Silva, Eduil Nascimento, David Menotti
Abstract
The advent of foundation models have enabled a new era in zero-shot classification. Yet, key challenges persist. Despite their impressive generalization power that leverages the immense pre-training knowledge, both foundation models for image and text as well as vision-text hybrids lack the representational power needed for fine-grained, minutiae-based class separation that some real-world tasks require. To address the current gaps in the literature, we propose VeriCam, a pipeline designed to learn highly specialized features that enable classification of unknown classes in unseen data. VeriCam works by leveraging the representation power of image models trained for the verification task, where the model develops an intricate feature space that incorporates fine-grained details. By training a model to discriminate between pairs of images from the same and different classes, a relational graph is constructed, representing the class relationships between data points. We then present two approaches for graph clustering: a naive algorithm and a specific setup for the Leiden graph clustering algorithm. The pipeline is validated on the LPLCv2 dataset, which comprises real-world traffic surveillance images. We show that the dataset carries an inherent capture device bias that is posed as a generalization challenge for downstream License Plate recognition tasks such as OCR. As such, we dynamically identify capture devices with a label-agnostic approach, enabling the construction of a fair and unbiased benchmark. In the cross-device scenario, our pipeline reaches an F1-Score of 93.45 in the verification baseline and a V-Measure score of 80.13 in the clustering step. All code is publicly available at https://github.com/lmlwojcik/VeriCam