Evaluating the Performance of Open-Vocabulary Object Detection in Low-quality Image
This work addresses the problem of robust object detection in real-world low-quality images for computer vision applications, but it is incremental as it focuses on evaluation rather than new methods.
The study evaluated open-vocabulary object detection models on low-quality images, finding that performance dropped sharply under high-level degradation, with OWLv2 models performing best and others declining significantly.
Open-vocabulary object detection enables models to localize and recognize objects beyond a predefined set of categories and is expected to achieve recognition capabilities comparable to human performance. In this study, we aim to evaluate the performance of existing models on open-vocabulary object detection tasks under low-quality image conditions. For this purpose, we introduce a new dataset that simulates low-quality images in the real world. In our evaluation experiment, we find that although open-vocabulary object detection models exhibited no significant decrease in mAP scores under low-level image degradation, the performance of all models dropped sharply under high-level image degradation. OWLv2 models consistently performed better across different types of degradation, while OWL-ViT, GroundingDINO, and Detic showed significant performance declines. We will release our dataset and codes to facilitate future studies.