Get Started
Research questionHow can parking-space classifiers generalize across visual environments with limited labeled target-domain data?Parking-space classifiers can perform poorly when camera views and visual conditions change between environments. Collecting enough labeled examples in every new environment is costly, while unlabeled data may be more readily available.
Computer Vision
Image & Video Processing
Machine Learning
Latest papersRecent research connected to this question, newest first.An Ensemble-Based Self-Taught Learning Approach for Parking Space Classification Under Limited DataThe source studies image-based parking-space classification using unlabeled data for representation learning and limited labeled samples in a target domain. Evidence comes from cross-dataset experiments on the PKLot and CNRPark benchmarks, reporting 93–96% accuracy in data-constrained settings.research paper · Sep 3, 2026
Related questions
How can vision systems discover unknown fine-grained classes without capture-device bias distorting cross-device evaluation?How can vision models trained on one labeled domain generalize to unseen domains with difficult, semantically valid variations?How can object detectors trained on uncamouflaged imagery generalize to unseen camouflage with little target-domain data?How can video models recognize unseen actions from only a few labeled examples?
Home
Topics
Search
Library